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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ジア
    -0.07
    095
    -0.07
    έν
    -0.07
    porno
    -0.06
    ียญ
    -0.06
    ذكر
    -0.06
    álně
    -0.06
    胎
    -0.06
     Thomson
    -0.06
    imizde
    -0.06
    POSITIVE LOGITS
     CLOSED
    0.06
     outdoor
    0.06
    aje
    0.06
    construct
    0.06
    _table
    0.06
    umed
    0.06
     Hij
    0.06
    setScale
    0.06
    .controls
    0.06
    DIFF
    0.05
    Act Density 0.006%

    No Known Activations