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

    Neuronpedia

    INDEX
    Explanations

    Mass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nesc
    -0.07
    _HAND
    -0.07
     appell
    -0.07
    >').
    -0.07
    isplay
    -0.07
    Comple
    -0.07
    FAQ
    -0.07
    olkien
    -0.07
    ifferent
    -0.07
     Appet
    -0.07
    POSITIVE LOGITS
    钍
    0.08
    Lists
    0.07
    밷
    0.07
     учитыва
    0.07
     zero
    0.07
    (slice
    0.07
    띵
    0.07
     både
    0.07
     ogłoszeni
    0.07
     série
    0.07
    Act Density 0.003%

    No Known Activations