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

    Neuronpedia

    INDEX
    Explanations

    Rounding numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Employee
    -0.07
    ди
    -0.06
     ard
    -0.06
    ová
    -0.06
    .reverse
    -0.06
     frozen
    -0.06
     rallied
    -0.06
    (df
    -0.06
    CANCEL
    -0.06
    aims
    -0.06
    POSITIVE LOGITS
    angles
    0.07
     requirement
    0.06
    assignments
    0.06
    -character
    0.06
     قرآن
    0.06
     interpretation
    0.06
     purchased
    0.06
    _regularizer
    0.06
    _perc
    0.06
    �
    0.06
    Act Density 0.004%

    No Known Activations