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

    Neuronpedia

    INDEX
    Explanations

    code and web development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    guided
    -0.07
     induction
    -0.07
     utilizing
    -0.06
     slips
    -0.06
     Canyon
    -0.06
    Digital
    -0.06
    "Yeah
    -0.06
     '!
    -0.06
     Collective
    -0.06
     Пав
    -0.06
    POSITIVE LOGITS
     rainy
    0.07
     atoms
    0.06
    ño
    0.06
    ↵    ↵    ↵
    0.06
    (platform
    0.06
    ไว
    0.06
    esidir
    0.06
     п
    0.06
    extends
    0.06
     عالی
    0.06
    Act Density 0.199%

    No Known Activations