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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Malone
    -0.07
     pan
    -0.06
    -index
    -0.06
     voiced
    -0.06
     ===
    -0.06
    .created
    -0.06
    @endforeach
    -0.06
    ’app
    -0.06
    checkout
    -0.06
    Requested
    -0.06
    POSITIVE LOGITS
     　 　 　 　 　 　
    0.06
    afür
    0.06
    akash
    0.06
     �
    0.06
    ::::::::::::::::::::::::::::::::
    0.06
    plementary
    0.06
     lực
    0.06
     超
    0.06
    ัฐ
    0.06
     extremist
    0.06
    Act Density 0.010%

    No Known Activations