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

    Neuronpedia

    INDEX
    Explanations

    unwanted sexual thoughts or urges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    体现
    0.39
    opro
    0.38
    odeal
    0.38
    ItemStack
    0.37
    审核
    0.37
    代謝
    0.36
    १८६
    0.36
     הר
    0.36
     Electrochemical
    0.36
    堭
    0.35
    POSITIVE LOGITS
    TRAILING
    0.37
    尴尬
    0.35
     गोवि
    0.35
     GTP
    0.35
     Kei
    0.35
     rigid
    0.34
     explosive
    0.34
     convincing
    0.34
    ્યૂ
    0.34
    啫
    0.34
    Act Density 0.010%

    No Known Activations