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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    promo
    -0.07
     HW
    -0.06
    lep
    -0.06
     банк
    -0.06
    ιας
    -0.06
    �
    -0.06
     viewType
    -0.06
    .descripcion
    -0.06
     reads
    -0.06
    なし
    -0.06
    POSITIVE LOGITS
     BEEN
    0.07
    ůst
    0.07
    unter
    0.07
    (Local
    0.06
     Gotham
    0.06
    Whenever
    0.06
    vědom
    0.06
     وش
    0.06
    502
    0.06
    _neurons
    0.06
    Act Density 0.026%

    No Known Activations