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

    Neuronpedia

    INDEX
    Explanations

    references to shared experiences and emotions

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

    simply truly indeed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.67
     calendriers
    -0.64
     Мексичка
    -0.63
    IntoConstraints
    -0.62
    DebuggerNonUser
    -0.58
     للمعارف
    -0.57
    LookAnd
    -0.55
     createSprite
    -0.55
    ormous
    -0.54
    saraba
    -0.53
    POSITIVE LOGITS
     ‘
    0.50
     “
    0.50
     truly
    0.49
    simply
    0.49
     simply
    0.45
    truly
    0.44
     indeed
    0.43
    !”
    0.43
    jspx
    0.42
    …
    0.42
    Act Density 0.036%

    No Known Activations