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

    Neuronpedia

    INDEX
    Explanations

    information requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Tests
    -0.06
     Rebecca
    -0.06
     cloning
    -0.06
    _HEALTH
    -0.06
     flights
    -0.06
    .SQL
    -0.06
    itude
    -0.06
     zk
    -0.06
    Cars
    -0.06
    scan
    -0.06
    POSITIVE LOGITS
    (blob
    0.07
     プロ
    0.07
    ูรณ
    0.06
     demonstr
    0.06
    ――
    0.06
    ี
    0.06
    (In
    0.06
    ，与
    0.06
     cuer
    0.06
    AtPath
    0.06
    Act Density 0.027%

    No Known Activations