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

    Neuronpedia

    INDEX
    Explanations

    composed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    親
    -0.07
    Popular
    -0.06
    (Language
    -0.06
    444
    -0.06
    <List
    -0.06
    fighters
    -0.06
    _ends
    -0.06
    八
    -0.06
    apos
    -0.06
    .ReadAllText
    -0.05
    POSITIVE LOGITS
    PLUGIN
    0.07
     FT
    0.07
     HB
    0.06
    圈
    0.06
     extracted
    0.06
     pac
    0.06
     фут
    0.06
     PACKET
    0.06
     заліз
    0.06
    ˆ
    0.06
    Act Density 0.021%

    No Known Activations