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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lü
    -0.07
     commuting
    -0.07
    _td
    -0.07
     thrilled
    -0.07
    บท
    -0.07
    ゅ
    -0.06
    utom
    -0.06
    SECRET
    -0.06
     genç
    -0.06
    arbon
    -0.06
    POSITIVE LOGITS
     maybe
    0.07
    ={[
    0.07
     ()
    0.06
    FPS
    0.06
    Cause
    0.06
     بده
    0.06
    .container
    0.06
    )didReceiveMemoryWarning
    0.06
    рач
    0.06
    Sel
    0.06
    Act Density 0.007%

    No Known Activations