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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ∨
    -0.07
    였다
    -0.07
    ∃
    -0.07
     componente
    -0.07
    โม
    -0.07
    Officials
    -0.06
    △
    -0.06
    博文
    -0.06
    .tooltip
    -0.06
     recovered
    -0.06
    POSITIVE LOGITS
     glEnable
    0.09
    洗澡
    0.08
     collided
    0.08
    סחר
    0.07
    苏州市
    0.07
    거래
    0.07
    띱
    0.07
    grammar
    0.07
     Terms
    0.07
    学费
    0.07
    Act Density 0.010%

    No Known Activations