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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (info
    -0.07
    ни
    -0.07
     ReturnType
    -0.07
    nio
    -0.07
    innie
    -0.06
     Flight
    -0.06
    ła
    -0.06
     Infinite
    -0.06
    v
    -0.06
    Date
    -0.06
    POSITIVE LOGITS
    嘛
    0.07
     наш
    0.07
    Disappear
    0.07
     çoğ
    0.06
    ulpt
    0.06
     nag
    0.06
     cms
    0.06
    .Cons
    0.06
     extensive
    0.06
     hak
    0.06
    Act Density 0.004%

    No Known Activations