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

    Neuronpedia

    INDEX
    Explanations

    contained

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Global
    -0.06
     apologized
    -0.06
     negatives
    -0.06
     Tales
    -0.06
    _VERBOSE
    -0.06
     McCabe
    -0.06
    ucus
    -0.06
    bras
    -0.06
    avan
    -0.06
    เพลง
    -0.06
    POSITIVE LOGITS
    "),"
    0.07
    <S
    0.07
    CSI
    0.07
    :`
    0.07
    @register
    0.07
    plementary
    0.06
     skutečnosti
    0.06
    ):?>↵
    0.06
    ैं.↵
    0.06
    :P
    0.06
    Act Density 0.006%

    No Known Activations