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

    Neuronpedia

    INDEX
    Explanations

    about different topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.53
     FISA
    0.43
     attentive
    0.42
     जाऊ
    0.42
     other
    0.41
    ede
    0.41
    nette
    0.41
    dataIn
    0.41
     calmly
    0.40
     FSH
    0.40
    POSITIVE LOGITS
    因
    0.44
    重大
    0.44
    द
    0.43
    ه
    0.43
    能力
    0.43
    اد
    0.42
    उ
    0.41
    ان
    0.39
    ن
    0.39
    ي
    0.38
    Act Density 0.488%

    No Known Activations