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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     licked
    -0.07
    .timing
    -0.07
     opposite
    -0.06
    Painter
    -0.06
    ery
    -0.06
     Ner
    -0.06
    _opacity
    -0.06
    stanbul
    -0.06
    臨
    -0.05
    みたい
    -0.05
    POSITIVE LOGITS
     WOW
    0.07
     польз
    0.07
    的
    0.07
    REDENTIAL
    0.07
     확실
    0.07
    ंय
    0.06
    XXXX
    0.06
     String
    0.06
     Owned
    0.06
     Musik
    0.06
    Act Density 0.017%

    No Known Activations