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

    Neuronpedia

    INDEX
    Explanations

    Gospels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Demand
    -0.07
     Control
    -0.07
    Certain
    -0.07
     Negot
    -0.06
     Alexander
    -0.06
    ナ
    -0.06
     Nine
    -0.06
     parents
    -0.06
    Negative
    -0.06
     Beispiel
    -0.06
    POSITIVE LOGITS
     đánh
    0.07
    veedor
    0.07
    ZX
    0.06
    。这
    0.06
    .zh
    0.06
     øns
    0.06
    ือน
    0.06
    _REPLY
    0.06
    isContained
    0.06
    _acl
    0.06
    Act Density 0.019%

    No Known Activations