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

    Neuronpedia

    INDEX
    Explanations

    offering suggestions, services, advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.47
    ก
    1.23
     може
    1.06
    о
    1.05
     estrogen
    1.00
     свое
    1.00
     т
    0.99
     հ
    0.98
     thổ
    0.98
     օ
    0.97
    POSITIVE LOGITS
    and
    1.59
    P
    1.41
    R
    1.41
    H
    1.34
    T
    1.34
    in
    1.33
    i
    1.32
    ﺭ
    1.30
    it
    1.27
    ’
    1.23
    Act Density 0.064%

    No Known Activations