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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intr
    -0.07
     olabilir
    -0.07
     Assign
    -0.06
     مالی
    -0.06
    иться
    -0.06
    ：「
    -0.06
     Gia
    -0.06
     sign
    -0.06
     He
    -0.06
     watering
    -0.06
    POSITIVE LOGITS
     WRITE
    0.07
    enght
    0.07
    IVED
    0.07
    (%
    0.07
     spontaneous
    0.07
     kleinen
    0.06
    شماری
    0.06
    steller
    0.06
    lilik
    0.06
    */,
    0.06
    Act Density 0.098%

    No Known Activations