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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Salary
    -0.07
    umar
    -0.07
    conversion
    -0.06
    _exam
    -0.06
     Αν
    -0.06
    recated
    -0.06
    .Total
    -0.06
     Em
    -0.06
     dosy
    -0.06
    Total
    -0.06
    POSITIVE LOGITS
    ...\
    0.07
    >Edit
    0.06
     Finds
    0.06
     cumbersome
    0.06
     Fahr
    0.06
    床
    0.06
    ('{}
    0.06
    일에
    0.06
    ffd
    0.06
    초등학교
    0.06
    Act Density 0.000%

    No Known Activations