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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     farine
    -0.07
     fabric
    -0.07
     lub
    -0.07
    (Uri
    -0.07
    Click
    -0.07
    <Action
    -0.07
    _Click
    -0.07
    .Click
    -0.07
     distress
    -0.07
     peligro
    -0.07
    POSITIVE LOGITS
     Motto
    0.08
     最
    0.08
    最
    0.08
     Tournament
    0.08
    Contest
    0.07
     Devils
    0.07
     değerlend
    0.07
     outperform
    0.07
     ganhos
    0.07
    iski
    0.07
    Act Density 0.007%

    No Known Activations