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

    Neuronpedia

    INDEX
    Explanations

    LICENSE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تد
    -0.09
    إش
    -0.08
     comerc
    -0.08
    瞀
    -0.07
    padding
    -0.07
     Arkadaş
    -0.07
     בהם
    -0.07
     forb
    -0.07
    晨报
    -0.07
    تض
    -0.07
    POSITIVE LOGITS
    斯顿
    0.08
     Ort
    0.08
    информационн
    0.07
    .model
    0.07
    溦
    0.07
     Largest
    0.07
     directional
    0.07
     reviewing
    0.07
    или
    0.06
    _dimension
    0.06
    Act Density 0.002%

    No Known Activations