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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    blr
    -0.07
     qq
    -0.06
    fp
    -0.06
     ek
    -0.06
    .sheet
    -0.06
     ovar
    -0.06
     kw
    -0.06
    ΑΚ
    -0.06
    myModal
    -0.06
     bree
    -0.06
    POSITIVE LOGITS
    (moment
    0.07
    Boolean
    0.07
    _threshold
    0.06
    Erot
    0.06
     robust
    0.06
    níku
    0.06
    част
    0.06
     konut
    0.06
    _DURATION
    0.06
    [sub
    0.06
    Act Density 0.015%

    No Known Activations