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

    Neuronpedia

    INDEX
    Explanations

    grammar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jud
    -0.07
    ullet
    -0.07
     dolls
    -0.07
    ucs
    -0.07
     ná
    -0.07
     hook
    -0.07
    ğmen
    -0.06
     Burlington
    -0.06
     düzey
    -0.06
     edged
    -0.06
    POSITIVE LOGITS
    toISOString
    0.07
    /react
    0.06
     UNIX
    0.06
    _generate
    0.06
    ▍
    0.06
    تن
    0.06
    _First
    0.06
    sett
    0.06
     irreversible
    0.05
     applying
    0.05
    Act Density 0.050%

    No Known Activations