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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irse
    -0.06
     timers
    -0.06
     الج
    -0.06
    =label
    -0.06
     DEL
    -0.06
     nuestra
    -0.06
    /lg
    -0.06
    �ت
    -0.06
     �
    -0.06
    _sum
    -0.06
    POSITIVE LOGITS
    milliseconds
    0.07
     포
    0.06
     Jenna
    0.06
    irth
    0.06
     death
    0.06
     Shelley
    0.06
     ",
    0.06
     offense
    0.06
    poster
    0.06
    she
    0.06
    Act Density 0.045%

    No Known Activations