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

    Neuronpedia

    INDEX
    Explanations

    courses and technical fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agona
    0.80
    боров
    0.79
     бў
    0.78
    Checksum
    0.77
    ósito
    0.77
    chh
    0.74
    Chance
    0.70
    után
    0.70
    ümler
    0.70
    foot
    0.70
    POSITIVE LOGITS
    襞
    0.80
     Typography
    0.75
    瘢
    0.74
     haus
    0.72
     shir
    0.72
     Mongolian
    0.71
     tai
    0.71
     Pollard
    0.71
     teori
    0.70
     jing
    0.70
    Act Density 0.023%

    No Known Activations