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

    Neuronpedia

    INDEX
    Explanations

    tomorrow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    νες
    0.49
    pregn
    0.46
    cult
    0.46
    ნ
    0.45
    ף
    0.45
     incorrectly
    0.43
    น
    0.43
    트
    0.43
    際に
    0.43
    nobyl
    0.43
    POSITIVE LOGITS
     HART
    0.44
     courteous
    0.44
     quicker
    0.42
     noch
    0.41
     ||
    0.41
    чению
    0.40
     "@
    0.40
     CMS
    0.40
     parochial
    0.39
     sendMessage
    0.39
    Act Density 0.003%

    No Known Activations