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

    Neuronpedia

    INDEX
    Explanations

    seeing in different languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ults
    -0.09
    ystal
    -0.08
    urations
    -0.08
    quad
    -0.08
    Crazy
    -0.07
    urate
    -0.07
    ulture
    -0.07
    .Volley
    -0.07
    orious
    -0.07
    ासाठी
    -0.07
    POSITIVE LOGITS
     угроз
    0.09
     veo
    0.09
     ẹni
    0.09
     смысл
    0.09
     видеть
    0.09
     vejo
    0.08
     zitten
    0.08
     Zee
    0.08
     EPC
    0.08
    发展的
    0.08
    Act Density 0.058%

    No Known Activations