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

    Neuronpedia

    INDEX
    Explanations

    dust bunny

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ク
    0.52
    武
    0.52
    ي
    0.49
    オーナー
    0.49
    オペ
    0.48
    ॓
    0.48
    л
    0.47
    સ્ક
    0.47
     universitet
    0.47
     Willem
    0.46
    POSITIVE LOGITS
    1
    0.53
    aso
    0.53
    Current
    0.50
    oju
    0.50
    ering
    0.49
     بط
    0.49
    olog
    0.49
    five
    0.48
    fif
    0.47
    rums
    0.47
    Act Density 0.001%

    No Known Activations