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

    Neuronpedia

    INDEX
    Explanations

    Code-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     κρα
    -0.07
     radial
    -0.07
    GY
    -0.07
     Protocol
    -0.06
    ’t
    -0.06
    ющее
    -0.06
    ccd
    -0.06
    IDA
    -0.06
    バイ
    -0.06
     reserves
    -0.06
    POSITIVE LOGITS
     js
    0.07
     mensagem
    0.06
     Amsterdam
    0.06
    -js
    0.06
     pesos
    0.06
    ,string
    0.06
     provincial
    0.06
    Help
    0.06
    .app
    0.06
    .clip
    0.06
    Act Density 0.977%

    No Known Activations