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

    Neuronpedia

    INDEX
    Explanations

    Country

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ании
    -0.07
     Пред
    -0.07
     red
    -0.07
    fad
    -0.07
     essa
    -0.06
    ሓ
    -0.06
    𩾃
    -0.06
     мне
    -0.06
    裙子
    -0.06
    ording
    -0.06
    POSITIVE LOGITS
     Classifier
    0.08
     avalanche
    0.08
    complexType
    0.07
     explosion
    0.07
    一百多
    0.07
    stype
    0.07
    清净
    0.07
    endors
    0.07
     asc
    0.07
    _RIGHT
    0.07
    Act Density 0.148%

    No Known Activations