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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    228
    -0.07
     threat
    -0.07
     slime
    -0.06
     derivative
    -0.06
    세
    -0.06
    547
    -0.06
     shelters
    -0.06
    ंपन
    -0.06
     sliding
    -0.06
    STREAM
    -0.06
    POSITIVE LOGITS
    ؟
    0.07
    .play
    0.07
     hunted
    0.06
     chuck
    0.06
    ділу
    0.06
     عبار
    0.06
     ČR
    0.06
     چگونه
    0.06
    >:</
    0.06
     캐
    0.06
    Act Density 0.027%

    No Known Activations