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

    Neuronpedia

    INDEX
    Explanations

    eye

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     texto
    -0.07
    ало
    -0.06
    getSize
    -0.06
     учрежд
    -0.06
     отмеч
    -0.06
     recruiter
    -0.06
     complic
    -0.06
     اک
    -0.06
     Damian
    -0.06
    stmt
    -0.06
    POSITIVE LOGITS
    (relative
    0.08
     Suspension
    0.06
    [x
    0.06
    :''
    0.06
     ({
    0.06
    ουσ
    0.06
    到的
    0.06
    emean
    0.06
    вержд
    0.06
    runs
    0.06
    Act Density 0.014%

    No Known Activations