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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     заходів
    -0.07
     ترین
    -0.06
    ;set
    -0.06
    ertificate
    -0.06
    ('(
    -0.06
    ild
    -0.06
     separator
    -0.06
     Kavanaugh
    -0.06
    38
    -0.06
     Sev
    -0.06
    POSITIVE LOGITS
     LANGUAGE
    0.07
     passwd
    0.07
    ź
    0.07
    /B
    0.07
    -В
    0.06
     Behavioral
    0.06
    esome
    0.06
    五
    0.06
     Physiology
    0.06
     bulletin
    0.06
    Act Density 0.352%

    No Known Activations