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

    Neuronpedia

    INDEX
    Explanations

    let's begin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Batik
    0.42
     BUT
    0.41
     ONLY
    0.40
     ANY
    0.39
     polynom
    0.39
     SEX
    0.38
     Training
    0.38
     NOW
    0.38
     YES
    0.38
     Labour
    0.37
    POSITIVE LOGITS
     صحبت
    0.51
    isie
    0.48
    今天
    0.46
     сегодня
    0.46
     sedikit
    0.46
    cerpt
    0.44
    amiliar
    0.42
     소개
    0.42
    ⁦
    0.42
    인데
    0.41
    Act Density 0.049%

    No Known Activations