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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alo
    -0.07
    dsl
    -0.07
     getUserId
    -0.07
    �
    -0.06
     Intellectual
    -0.06
     put
    -0.06
    approx
    -0.06
     Disposable
    -0.06
     disruptions
    -0.06
    .Sequential
    -0.06
    POSITIVE LOGITS
    _Config
    0.06
    /math
    0.06
    dikleri
    0.06
     wxDefault
    0.06
     الانت
    0.06
     {
↵
    0.06
     Theo
    0.06
     		↵
    0.06
    /use
    0.06
    ades
    0.06
    Act Density 0.030%

    No Known Activations