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

    Neuronpedia

    INDEX
    Explanations

    unsupported

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ounding
    -0.07
    (cv
    -0.07
    INGS
    -0.07
    _DAYS
    -0.07
    Nombre
    -0.07
    icking
    -0.07
    consume
    -0.07
    KeyName
    -0.07
    _DONE
    -0.07
    نسان
    -0.06
    POSITIVE LOGITS
     unsupported
    0.08
    unsupported
    0.07
     professions
    0.07
    recogn
    0.07
    ]):↵
    0.06
    beth
    0.06
     deduct
    0.06
    (origin
    0.06
     afirm
    0.06
    /us
    0.06
    Act Density 0.005%

    No Known Activations