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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -hop
    -0.08
    -ul
    -0.07
    -ind
    -0.07
    -B
    -0.07
    issan
    -0.07
    "Yeah
    -0.06
    介
    -0.06
    -C
    -0.06
    -H
    -0.06
    ी-
    -0.06
    POSITIVE LOGITS
    rought
    0.06
    allas
    0.06
    Ⅵ
    0.06
    _crit
    0.06
     cp
    0.06
     отли
    0.06
     trä
    0.06
     продолж
    0.06
    NAME
    0.06
    _HASH
    0.06
    Act Density 0.216%

    No Known Activations