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

    Neuronpedia

    INDEX
    Explanations

    AI assistant refusing requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jadi
    0.47
    ibusdam
    0.46
    gmzy
    0.45
    itabbo
    0.43
    ại
    0.43
    ontiti
    0.43
    iotsitewise
    0.42
     சர்வதேச
    0.42
     ልዩ
    0.42
    rta
    0.42
    POSITIVE LOGITS
     syndrome
    0.53
     symptoms
    0.48
     counter
    0.47
     clutter
    0.46
     capable
    0.45
     thwart
    0.45
     border
    0.44
     creatures
    0.43
     creature
    0.43
     speaker
    0.43
    Act Density 0.140%

    No Known Activations