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

    Neuronpedia

    INDEX
    Explanations

    InputStream

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ∋
    -0.07
     kot
    -0.07
     pockets
    -0.07
    隶属于
    -0.07
    范
    -0.07
     mans
    -0.06
    扶
    -0.06
    ることは
    -0.06
     knees
    -0.06
     celebrities
    -0.06
    POSITIVE LOGITS
    _format
    0.07
    %timeout
    0.07
    _lost
    0.06
    .alibaba
    0.06
    _motion
    0.06
     UCS
    0.06
    ólica
    0.06
     anos
    0.06
    문화
    0.06
     empir
    0.06
    Act Density 0.006%

    No Known Activations