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

    Neuronpedia

    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     washer
    -0.85
     washers
    -0.73
     Washer
    -0.67
    ared
    -0.59
    iding
    -0.57
    protoimpl
    -0.54
    washer
    -0.54
     समीक्षक
    -0.50
    bufio
    -0.49
    isAlive
    -0.49
    POSITIVE LOGITS
    Personensuche
    0.71
    RegistryLite
    0.62
     ISNI
    0.60
    LookAnd
    0.60
     Roskov
    0.59
    rix
    0.55
     tolerated
    0.52
     joaat
    0.51
    Напомним
    0.51
     limon
    0.51
    Act Density 0.019%

    No Known Activations