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

    Neuronpedia

    INDEX
    Explanations

    words associated with inappropriate or adult themes

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

    ending in "ck"

    np_acts-logits-general · gemini-2.0-flash

    names and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PyExc
    -0.65
     disambiguazione
    -0.63
    phrine
    -0.58
    thâu
    -0.57
    zation
    -0.54
    prakti
    -0.51
    colin
    -0.50
     LUMP
    -0.49
    mstyle
    -0.49
    StoryboardSegue
    -0.48
    POSITIVE LOGITS
    ety
    0.96
    eting
    0.96
    iest
    0.94
    ets
    0.92
    ers
    0.90
    ed
    0.88
    ery
    0.86
    kkkk
    0.86
    ie
    0.85
    ett
    0.84
    Act Density 0.271%

    No Known Activations