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

    Neuronpedia

    INDEX
    Explanations

    types of recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    manes
    0.44
    圈
    0.39
     ज
    0.38
     (
    0.36
    ロット
    0.35
     lengths
    0.35
    lengths
    0.35
     careful
    0.34
     रे
    0.34
    维
    0.34
    POSITIVE LOGITS
     الدولية
    0.44
    sekut
    0.41
     eur
    0.40
    arabic
    0.40
    📒
    0.40
    sinatra
    0.39
    <unused98>
    0.39
     बंगला
    0.39
     здоровье
    0.39
    👛
    0.39
    Act Density 0.000%

    No Known Activations