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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    citation
    -0.07
    ities
    -0.06
     ústav
    -0.06
    uploader
    -0.06
     BEN
    -0.06
    ior
    -0.06
     -----------
    -0.06
    ITIES
    -0.06
     sunshine
    -0.06
    __;
    -0.06
    POSITIVE LOGITS
    /************************
    0.06
    rey
    0.06
    -secret
    0.06
    点击
    0.06
    merchant
    0.06
    (handler
    0.06
    .this
    0.06
    aleigh
    0.06
     باید
    0.06
     должна
    0.06
    Act Density 0.054%

    No Known Activations