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

    Neuronpedia

    INDEX
    Explanations

    code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orientation
    -0.07
     candidates
    -0.06
     Utt
    -0.06
    .endDate
    -0.06
     Economy
    -0.06
     armour
    -0.06
    .om
    -0.06
    andidates
    -0.06
     Kazakhstan
    -0.06
     가까
    -0.06
    POSITIVE LOGITS
     stripslashes
    0.07
    Drupal
    0.06
     تجربه
    0.06
    .GraphicsUnit
    0.06
    parable
    0.06
    _sibling
    0.06
    чів
    0.06
    _literal
    0.06
     مستقیم
    0.06
     paralle
    0.06
    Act Density 0.001%

    No Known Activations