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

    Neuronpedia

    INDEX
    Explanations

    anecdotes and memories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    compatible
    -0.07
    rends
    -0.07
     tình
    -0.07
    (Input
    -0.07
     jot
    -0.06
     답변
    -0.06
     phái
    -0.06
    /desktop
    -0.06
    JNI
    -0.06
    -al
    -0.06
    POSITIVE LOGITS
    Houston
    0.08
     Houston
    0.07
     Rhe
    0.07
    .Last
    0.06
     Exposure
    0.06
    。不过
    0.06
     river
    0.06
     Sask
    0.06
     north
    0.06
    Ir
    0.06
    Act Density 0.179%

    No Known Activations