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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.06
    -0.06
    044
    -0.06
     boosted
    -0.06
    -0.06
    _fake
    -0.06
    -0.06
     Fortunately
    -0.06
    -0.06
    Descri
    -0.06
    POSITIVE LOGITS
    �
    0.07
     each
    0.07
    [].
    0.07
     ctl
    0.06
     Horm
    0.06
     toString
    0.06
    ие
    0.06
    献
    0.06
    .visitInsn
    0.06
    contact
    0.06
    Act Density 0.020%

    No Known Activations