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

    Neuronpedia

    INDEX
    Explanations

    customize it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    g
    0.48
     Trauma
    0.46
     Dirty
    0.45
     psychopath
    0.45
     PSY
    0.45
     ((
    0.44
    ath
    0.44
    ЕД
    0.44
     (((
    0.43
    nar
    0.43
    POSITIVE LOGITS
    样式
    0.53
     equalize
    0.49
    风格
    0.45
     stockings
    0.44
    effetto
    0.44
    પ્ર
    0.43
    个性
    0.43
    整体
    0.43
    绒
    0.43
    মূলক
    0.42
    Act Density 0.002%

    No Known Activations