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

    Neuronpedia

    INDEX
    Explanations

    mimic or mimics behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enmity
    0.47
    зим
    0.46
     골
    0.46
     życia
    0.46
    ช
    0.45
     wear
    0.45
    어
    0.45
     แล้ว
    0.45
     externalities
    0.45
     gowns
    0.45
    POSITIVE LOGITS
    র্ঘট
    0.47
    background
    0.46
    ge
    0.45
    的研究
    0.45
    ả
    0.44
    avasena
    0.42
    vos
    0.42
    ourage
    0.42
     నేపథ
    0.42
     Scanner
    0.42
    Act Density 0.000%

    No Known Activations