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

    Neuronpedia

    INDEX
    Explanations

    quantification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dental
    -0.07
    On
    -0.07
     On
    -0.06
     horn
    -0.06
     Voldemort
    -0.06
     bày
    -0.06
     correcting
    -0.06
     FROM
    -0.06
    Prob
    -0.06
    ologi
    -0.06
    POSITIVE LOGITS
    (man
    0.07
    _HAS
    0.07
     pyt
    0.07
     діяльності
    0.06
     درد
    0.06
    (ErrorMessage
    0.06
    "She
    0.06
    अ
    0.06
    ='"
    0.06
    flare
    0.06
    Act Density 0.209%

    No Known Activations