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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating joining or approaching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ścic
    1.12
    ม
    1.03
     비롯
    1.02
    ्यवाद
    0.99
    یوں
    0.99
    𝐚
    0.98
    納税
    0.96
    आई
    0.95
     खान
    0.95
    人民币
    0.95
    POSITIVE LOGITS
    .
    1.17
    :
    1.06
    n
    0.98
    t
    0.92
    !
    0.89
    _
    0.86
    ?
    0.86
    {
    0.84
    -
    0.82
    ie
    0.81
    Act Density 0.049%

    No Known Activations