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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Washington
    -0.07
     Mothers
    -0.07
    eat
    -0.07
     Like
    -0.07
     CZ
    -0.07
     detox
    -0.06
     Krish
    -0.06
     Fellowship
    -0.06
    峰
    -0.06
     respecto
    -0.06
    POSITIVE LOGITS
     Lebens
    0.06
     بیرون
    0.06
    gons
    0.06
     meine
    0.06
    (State
    0.06
    lookup
    0.06
    naire
    0.06
    ží
    0.06
    (Type
    0.06
    .getMin
    0.06
    Act Density 0.009%

    No Known Activations