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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ultr
    -0.07
    Fred
    -0.07
    embed
    -0.07
    serialization
    -0.06
    Cont
    -0.06
    aign
    -0.06
    Carbon
    -0.06
    ENSE
    -0.06
    権
    -0.06
    mana
    -0.06
    POSITIVE LOGITS
    //************************************************************************
    0.07
    (freq
    0.06
     tarihi
    0.06
    _category
    0.06
     Category
    0.06
     was
    0.06
     Kimberly
    0.06
    .showError
    0.06
    _DURATION
    0.05
     McGr
    0.05
    Act Density 0.002%

    No Known Activations