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

    Neuronpedia

    INDEX
    Explanations

    text discussing charity work towards children and other community support

    oai_token-act-pair · gemini-2.0-flash

    charitable organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '{@
    -0.60
    CppMethod
    -0.56
    oplayer
    -0.52
    bille
    -0.50
    }>;
    -0.49
    cha
    -0.48
     springfox
    -0.47
     Diar
    -0.47
     cellpadding
    -0.47
    زین
    -0.47
    POSITIVE LOGITS
    IsContent
    0.66
    uxxxx
    0.63
    Clik
    0.59
    OGND
    0.54
    Vidite
    0.54
    FormTagHelper
    0.53
    unesse
    0.52
    0.52
    InitVars
    0.48
    ToAction
    0.48
    Act Density 0.863%

    No Known Activations