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

    Neuronpedia

    INDEX
    Explanations

    science research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sapphire
    -0.07
     insured
    -0.07
     scanner
    -0.07
    ucky
    -0.07
     zem
    -0.07
     repeated
    -0.06
     درس
    -0.06
    peated
    -0.06
     печ
    -0.06
     thuế
    -0.06
    POSITIVE LOGITS
    than
    0.06
    Employ
    0.06
    �
    0.06
    Fund
    0.06
     contribute
    0.06
     関連
    0.06
     professionals
    0.06
    (val
    0.06
    zyst
    0.06
    toHaveBeenCalledTimes
    0.06
    Act Density 0.075%

    No Known Activations