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

    Neuronpedia

    INDEX
    Explanations

    explanation comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    percentages
    0.35
    }`))
    0.35
    Seats
    0.34
     washout
    0.32
     wastage
    0.32
    ühlt
    0.32
    })-(\
    0.32
    Typical
    0.31
    尺度
    0.31
    clementine
    0.31
    POSITIVE LOGITS
     ذات
    0.36
    ાદ
    0.36
     掛け
    0.36
     Curriculum
    0.35
     દે
    0.34
     thiết
    0.33
     tên
    0.33
    adhi
    0.33
     file
    0.33
     Arch
    0.33
    Act Density 0.004%

    No Known Activations