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

    Neuronpedia

    INDEX
    Explanations

    poisson distribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =@
    -0.07
     온
    -0.07
    Where
    -0.06
     JW
    -0.06
    gmail
    -0.06
    lol
    -0.06
    "How
    -0.06
    itempty
    -0.06
    "@
    -0.06
     stron
    -0.06
    POSITIVE LOGITS
     trying
    0.07
    Tiny
    0.07
    Ш
    0.07
     Pří
    0.07
    orama
    0.07
     अपर
    0.07
    (platform
    0.07
    อง
    0.06
    収
    0.06
    回来
    0.06
    Act Density 0.016%

    No Known Activations