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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     개
    -0.08
     сочет
    -0.08
    視
    -0.07
    ƃ
    -0.07
     псих
    -0.07
     внутри
    -0.07
    失控
    -0.07
     בעצם
    -0.07
    наци
    -0.07
    一方
    -0.07
    POSITIVE LOGITS
    "]))
    0.07
     Equal
    0.07
     olds
    0.07
    mapped
    0.07
    birds
    0.07
     ”
    0.07
    cul
    0.07
    (`/
    0.07
    requently
    0.06
    -outs
    0.06
    Act Density 0.008%

    No Known Activations