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

    Neuronpedia

    INDEX
    Explanations

    animal abuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wyman
    0.46
     sowohl
    0.45
    bq
    0.44
    াক্রমে
    0.43
    umlahan
    0.40
    }}^{\
    0.40
    डब्ल्यू
    0.40
     Gustaf
    0.39
     verfügen
    0.38
     zugleich
    0.38
    POSITIVE LOGITS
    جی
    0.50
     intently
    0.47
    Condition
    0.46
    dove
    0.43
    Ė
    0.42
    hele
    0.41
    segn
    0.41
    Пре
    0.41
     hyperfine
    0.41
    첫
    0.40
    Act Density 0.013%

    No Known Activations