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

    Neuronpedia

    INDEX
    Explanations

    pronunciation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     claiming
    -0.07
     grandfather
    -0.07
     Dios
    -0.06
    _array
    -0.06
    ByteArray
    -0.06
    Nation
    -0.06
     INFORMATION
    -0.06
     chapter
    -0.06
     RADIO
    -0.06
    λλά
    -0.06
    POSITIVE LOGITS
    olvimento
    0.07
     zurück
    0.06
    (inner
    0.06
    <F
    0.06
    _sur
    0.06
    *h
    0.06
    *g
    0.06
    /tr
    0.06
    ddf
    0.06
    YG
    0.06
    Act Density 0.008%

    No Known Activations