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

    Neuronpedia

    INDEX
    Explanations

    programming questions in other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gains
    -0.07
    Das
    -0.07
    ころ
    -0.07
    огда
    -0.07
     standardized
    -0.07
    ยว
    -0.06
     dazu
    -0.06
    Remarks
    -0.06
    �
    -0.06
     Throws
    -0.06
    POSITIVE LOGITS
    []={
    0.07
    booking
    0.06
     Сан
    0.06
    etroit
    0.06
    Aug
    0.06
     stepper
    0.06
    dist
    0.06
    -agent
    0.06
     complete
    0.06
    lav
    0.06
    Act Density 0.165%

    No Known Activations