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

    Neuronpedia

    INDEX
    Explanations

    say "don't"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "@"
    -0.07
     shortest
    -0.07
     Greenwood
    -0.07
    带
    -0.07
     вод
    -0.06
    GetProperty
    -0.06
     Generally
    -0.06
    (""
    -0.06
     nebude
    -0.06
    (Photo
    -0.06
    POSITIVE LOGITS
    isi
    0.07
     gratuiti
    0.07
    keypress
    0.06
    บล
    0.06
     zen
    0.06
    _gem
    0.06
     Sunny
    0.06
    .Navigation
    0.06
    ichi
    0.06
     комплек
    0.06
    Act Density 0.066%

    No Known Activations