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

    Neuronpedia

    INDEX
    Explanations

    references to specific object-oriented programming attributes and methods

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

    JavaScript property and type checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sén
    -0.42
     Kugel
    -0.41
    glEnd
    -0.40
    oneg
    -0.40
     check
    -0.40
    subplots
    -0.40
     tune
    -0.40
    tou
    -0.39
     tong
    -0.39
     Togo
    -0.39
    POSITIVE LOGITS
     csrf
    1.37
    csrf
    1.33
     CSRF
    1.03
    CSRF
    1.01
    Diweddarwch
    0.78
     Roskov
    0.66
     autorytatywna
    0.66
     invokingState
    0.62
     Administrativna
    0.60
    WriteBarrier
    0.58
    Act Density 0.001%

    No Known Activations