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

    Neuronpedia

    INDEX
    Explanations

    late or continuous running

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ful
    0.42
    .,
    0.38
     protruding
    0.38
    rote
    0.37
    !
    0.36
    Mrs
    0.36
    촘
    0.35
    trailing
    0.35
     замы
    0.35
    ct
    0.35
    POSITIVE LOGITS
     Bedingungen
    0.53
    其他人
    0.49
     distinctions
    0.48
     Fällen
    0.47
     другим
    0.47
     Optionen
    0.46
    ี้ย
    0.46
    нном
    0.45
     సన్ని
    0.45
    ตั้งแต่
    0.45
    Act Density 0.001%

    No Known Activations