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

    Neuronpedia

    INDEX
    Explanations

    process descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    군
    -0.07
     fans
    -0.07
     goes
    -0.07
     serves
    -0.06
    ुप
    -0.06
    це
    -0.06
     amb
    -0.06
    др
    -0.06
    Hits
    -0.06
     fret
    -0.06
    POSITIVE LOGITS
    @Repository
    0.07
    ,label
    0.06
     форм
    0.06
    [],↵
    0.06
     compliments
    0.06
    олай
    0.06
    _fname
    0.06
     Nebraska
    0.06
    rubu
    0.06
    .↵↵↵↵↵↵↵↵
    0.06
    Act Density 0.108%

    No Known Activations