Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of affection or admiration for people, writing, and artistic styles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "I loved how"

    np_acts-logits-general · gemini-2.0-flash

    how beautifully, how real, how meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feroit
    -0.70
    UnsafeEnabled
    -0.67
    KommentareTeilen
    -0.65
     auroit
    -0.63
     myſelf
    -0.59
    urlpatterns
    -0.58
    IsContent
    -0.58
     pouvoit
    -0.58
     fortunately
    -0.58
     ferons
    -0.56
    POSITIVE LOGITS
     simplicity
    0.72
     dedication
    0.70
     sheer
    0.64
     willingness
    0.61
     cách
    0.60
     dedicated
    0.58
     enthusiasm
    0.58
     creativity
    0.57
     attitude
    0.55
     creative
    0.55
    Act Density 0.180%

    No Known Activations