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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    夜
    -0.08
     Genesis
    -0.08
    こと
    -0.07
     most
    -0.07
    deliver
    -0.07
     collisions
    -0.07
     naturalmente
    -0.07
     eyesight
    -0.07
     gece
    -0.07
     nights
    -0.07
    POSITIVE LOGITS
     günst
    0.08
     вър
    0.08
     yay
    0.08
    >(↵
    0.08
     Perspekt
    0.08
     खुशी
    0.08
     guitar
    0.07
     Percent
    0.07
     asupra
    0.07
     Exception
    0.07
    Act Density 0.016%

    No Known Activations