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

    Neuronpedia

    INDEX
    Explanations

    code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ssa
    -0.06
    �
    -0.06
    �
    -0.06
     suis
    -0.06
     terrible
    -0.06
    .Visible
    -0.06
    /title
    -0.06
    .pow
    -0.06
     Respons
    -0.06
     wholesalers
    -0.06
    POSITIVE LOGITS
    315
    0.07
     ang
    0.07
    iability
    0.06
     resume
    0.06
     留
    0.06
     cook
    0.06
    γωγή
    0.06
    通知
    0.06
    afort
    0.06
    ерж
    0.06
    Act Density 0.000%

    No Known Activations