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

    Neuronpedia

    INDEX
    Explanations

    reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pit
    -0.07
    pas
    -0.06
     vicious
    -0.06
    iac
    -0.06
    ीब
    -0.06
    šti
    -0.06
     πάνω
    -0.06
    _SKIP
    -0.06
    .spin
    -0.06
    nět
    -0.06
    POSITIVE LOGITS
     周
    0.06
     Charlotte
    0.06
     район
    0.06
     ор
    0.06
     TRI
    0.06
    标
    0.06
    TERN
    0.06
     motions
    0.06
    -----↵
    0.06
     Documentation
    0.06
    Act Density 0.004%

    No Known Activations