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

    Neuronpedia

    INDEX
    Explanations

    van

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    િ
    0.69
    崚
    0.67
     नवम्बर
    0.66
    花
    0.65
    に通
    0.62
    strip
    0.61
     않는
    0.59
    <0x91>
    0.56
     an
    0.56
    з
    0.55
    POSITIVE LOGITS
    am
    1.11
    ou
    0.96
    ot
    0.96
    at
    0.91
     hoeveel
    0.82
    ut
    0.80
    ar
    0.79
    um
    0.79
    ok
    0.76
    OS
    0.73
    Act Density 0.001%

    No Known Activations