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

    Neuronpedia

    INDEX
    Explanations

    Drilling Down on Digital

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setKeepCallback
    0.42
    사가
    0.42
    ioen
    0.41
    mPreview
    0.41
     ನಡೆದ
    0.41
    शिंगटन
    0.40
    捨て
    0.40
    గి
    0.39
    線を
    0.39
    饌
    0.39
    POSITIVE LOGITS
    _
    0.60
    d
    0.50
    ing
    0.47
     them
    0.46
    Ext
    0.45
     parasites
    0.45
    Z
    0.45
    app
    0.43
     oc
    0.42
    Tab
    0.42
    Act Density 0.015%

    No Known Activations