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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vocab
    -0.07
    finity
    -0.07
     signer
    -0.07
    ,image
    -0.06
    odos
    -0.06
    ,param
    -0.06
    _review
    -0.06
    $url
    -0.06
    :System
    -0.06
    ooky
    -0.06
    POSITIVE LOGITS
     chương
    0.07
     giai
    0.06
     міг
    0.06
     ω
    0.06
    china
    0.06
     perché
    0.06
    娱乐
    0.06
    onec
    0.06
    Argument
    0.06
     secondary
    0.06
    Act Density 0.000%

    No Known Activations