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

    Neuronpedia

    INDEX
    Explanations

    technical implementations and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mnogo
    0.45
     sculpture
    0.43
    σεων
    0.43
    πτωση
    0.43
    ેશ
    0.43
    সারণ
    0.43
    ophyllum
    0.42
    鈾
    0.42
    scalar
    0.42
     nanom
    0.42
    POSITIVE LOGITS
    ing
    0.45
    ర్
    0.44
     Lösungen
    0.43
    irme
    0.43
    Kelly
    0.42
    Partial
    0.42
    _
    0.42
    ">
    0.42
    খাস্ত
    0.42
    ਂ
    0.42
    Act Density 0.003%

    No Known Activations