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

    Neuronpedia

    INDEX
    Explanations

    digital innovation exchange

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    髮
    0.44
    Measure
    0.43
    ش
    0.42
    锵
    0.42
    颜色
    0.40
    Countdown
    0.39
     Days
    0.39
     Crisp
    0.38
    锋
    0.38
     dials
    0.38
    POSITIVE LOGITS
     mediates
    0.48
     negotiate
    0.48
    ತನ
    0.47
     through
    0.47
     negotiating
    0.46
     recombinant
    0.46
     multinational
    0.46
    through
    0.45
     negotiated
    0.45
     carv
    0.45
    Act Density 0.004%

    No Known Activations