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

    Neuronpedia

    INDEX
    Explanations

    updating contact information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xml
    -0.08
    NG
    -0.07
     Blind
    -0.07
     آنجا
    -0.06
    ився
    -0.06
    _TC
    -0.06
    ρια
    -0.06
    morgan
    -0.06
     Alaska
    -0.06
     spécial
    -0.06
    POSITIVE LOGITS
     pert
    0.06
    .Alignment
    0.06
     counterpart
    0.06
     onFinish
    0.06
     Βασ
    0.06
    VertexUvs
    0.06
     profiling
    0.06
    etail
    0.06
     wheelchair
    0.06
     San
    0.06
    Act Density 0.074%

    No Known Activations