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

    Neuronpedia

    INDEX
    Explanations

    Pol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cassidy
    -0.07
     Julio
    -0.07
     handguns
    -0.06
    Nobody
    -0.06
    _mtime
    -0.06
     Jeh
    -0.06
    nutí
    -0.06
    одо
    -0.06
    uste
    -0.06
     Ki
    -0.06
    POSITIVE LOGITS
     unfolding
    0.07
     address
    0.07
     CSC
    0.07
     listened
    0.07
     scripting
    0.06
     تلفن
    0.06
     education
    0.06
    �
    0.06
    .AI
    0.06
    .]↵↵
    0.06
    Act Density 0.013%

    No Known Activations