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

    Neuronpedia

    INDEX
    Explanations

    comment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Assange
    -0.08
     entrepreneurial
    -0.07
     Paid
    -0.07
     competitions
    -0.07
    \"]
    -0.06
     posX
    -0.06
     Sampler
    -0.06
     Money
    -0.06
    Changed
    -0.06
    .Binding
    -0.06
    POSITIVE LOGITS
     Mostly
    0.07
    (enc
    0.06
     click
    0.06
     cancelButtonTitle
    0.06
     mettre
    0.06
     styles
    0.06
     Nel
    0.06
    .round
    0.06
    referer
    0.06
     कहत
    0.06
    Act Density 0.006%

    No Known Activations