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

    Neuronpedia

    INDEX
    Explanations

    Undressing/sexual acts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     aprend
    -0.07
     Create
    -0.07
    .Enc
    -0.07
     vorhand
    -0.07
    优质
    -0.07
     Map
    -0.07
     bakım
    -0.07
     şu
    -0.07
    paramref
    -0.07
    POSITIVE LOGITS
     ((_
    0.07
     Wis
    0.07
    슷
    0.06
    密
    0.06
    êt
    0.06
    ***↵↵
    0.06
     _↵
    0.06
    inters
    0.06
    Rules
    0.06
     interrupts
    0.06
    Act Density 0.039%

    No Known Activations