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

    Neuronpedia

    INDEX
    Explanations

    specific names or labels associated with entities or characters in a context

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

    Vivek Oberoi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     skå
    -0.43
     Escolar
    -0.43
    mpotent
    -0.43
    racite
    -0.42
     Ellington
    -0.39
     endblock
    -0.38
    انيف
    -0.38
     Harlow
    -0.38
     etui
    -0.38
    Ethanol
    -0.38
    POSITIVE LOGITS
     Vive
    1.66
    Vive
    1.46
     Vivek
    0.98
     vive
    0.96
     Swami
    0.81
     ViewPager
    0.80
    ViewState
    0.79
    vive
    0.77
    logits
    0.69
    GOTREF
    0.67
    Act Density 0.003%

    No Known Activations