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

    Neuronpedia

    INDEX
    Explanations

    ladlip, PSF, Um_, Nayram, smf, This is, TagCommander

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    手的
    0.30
    اك
    0.27
    ળો
    0.26
    ।'
    0.26
    ából
    0.26
    ഗ്രഹം
    0.25
    ील
    0.25
     pretzels
    0.25
     needy
    0.25
     pressão
    0.24
    POSITIVE LOGITS
    -
    0.36
    _
    0.35
    tr
    0.32
    cb
    0.30
    bn
    0.29
    im
    0.27
    bl
    0.26
    ne
    0.26
    sw
    0.26
    sl
    0.26
    Act Density 0.112%

    No Known Activations