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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Truly
    -0.07
     đương
    -0.07
     Yeah
    -0.06
    など
    -0.06
     Qin
    -0.06
     tamaño
    -0.06
    หม
    -0.06
     TPP
    -0.06
     vér
    -0.06
    ;t
    -0.06
    POSITIVE LOGITS
    _COM
    0.07
    Json
    0.06
    jec
    0.06
    cludes
    0.06
     fetched
    0.06
    /mp
    0.06
     losses
    0.06
    wed
    0.06
    &ZeroWidthSpace
    0.06
    功能
    0.06
    Act Density 0.052%

    No Known Activations