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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    You
    -0.06
    _slider
    -0.06
    airobi
    -0.06
    彼
    -0.06
     prvním
    -0.06
    /INFO
    -0.06
    จะเป
    -0.06
    perhaps
    -0.06
     laten
    -0.06
     브
    -0.06
    POSITIVE LOGITS
    ги
    0.07
    ian
    0.07
    ATED
    0.07
    idential
    0.07
    kie
    0.06
    얼
    0.06
    .В
    0.06
     Immigration
    0.06
    VID
    0.06
    ESS
    0.06
    Act Density 0.006%

    No Known Activations