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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NPR
    -0.06
     writes
    -0.06
    Ｃ
    -0.06
    ovan
    -0.06
     quiz
    -0.06
     minions
    -0.06
    _eg
    -0.06
     qualifiers
    -0.06
    .Tests
    -0.06
    _sg
    -0.06
    POSITIVE LOGITS
    pite
    0.07
    companyId
    0.07
    �
    0.07
    اعب
    0.06
    !",
    0.06
     соблюд
    0.06
     ing
    0.06
    �
    0.06
     Gust
    0.06
    -fat
    0.06
    Act Density 0.000%

    No Known Activations