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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ários
    -0.07
     �
    -0.07
     unary
    -0.07
     dá
    -0.07
     inset
    -0.07
     ศร
    -0.06
     Unary
    -0.06
     Has
    -0.06
     predictor
    -0.06
    ificant
    -0.06
    POSITIVE LOGITS
    ЛА
    0.06
     曰
    0.06
     fresh
    0.06
    ーフ
    0.05
    -reg
    0.05
     carp
    0.05
    liqu
    0.05
    gage
    0.05
    =ax
    0.05
    morph
    0.05
    Act Density 0.037%

    No Known Activations