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

    Neuronpedia

    INDEX
    Explanations

    describing appearance or defining goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caters
    0.46
     undergoes
    0.43
     novedades
    0.43
     paves
    0.41
     Jahrhunderts
    0.41
     mutation
    0.41
     innovations
    0.40
     genome
    0.40
     novedad
    0.40
     produces
    0.39
    POSITIVE LOGITS
    Herb
    0.49
    Allan
    0.49
    Flame
    0.47
     سعی
    0.45
    Honey
    0.43
     שט
    0.43
    Fl
    0.42
    Need
    0.42
    Florida
    0.42
    Saturday
    0.42
    Act Density 0.000%

    No Known Activations