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

    Neuronpedia

    INDEX
    Explanations

    key and list elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    August
    0.40
    abre
    0.39
    mins
    0.39
    idity
    0.38
     abortion
    0.37
     August
    0.37
    ibus
    0.37
    htt
    0.37
    xml
    0.36
    id
    0.35
    POSITIVE LOGITS
     >>=
    0.43
     जानेंगे
    0.42
    科學
    0.42
     επισ
    0.42
     scientifique
    0.42
     ሌ
    0.42
     scientifiques
    0.41
     胡
    0.41
    牰
    0.40
     الدرا
    0.39
    Act Density 0.000%

    No Known Activations