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

    Neuronpedia

    INDEX
    Explanations

    ISBN and publication identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    事实上
    0.36
    만을
    0.35
    %);
    0.35
     plucked
    0.34
     çalış
    0.33
     pioneered
    0.33
     પ્રમા
    0.33
     harvested
    0.33
     annet
    0.32
     باتیں
    0.32
    POSITIVE LOGITS
     Fare
    0.38
     Cadillac
    0.36
     огром
    0.36
    CDM
    0.36
    IDO
    0.35
    ൦
    0.35
     ого
    0.35
    )',
    0.35
     OCLC
    0.35
    zoic
    0.34
    Act Density 0.001%

    No Known Activations