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

    Neuronpedia

    INDEX
    Explanations

    part of speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     predictive
    0.47
     forecasted
    0.46
    rible
    0.45
     whatnot
    0.45
     backlit
    0.43
    rence
    0.41
    วัฒ
    0.41
     листо
    0.40
    ari
    0.40
     traceability
    0.40
    POSITIVE LOGITS
     AVER
    0.50
     Monterey
    0.50
     özellikle
    0.50
     houve
    0.48
     dificuldades
    0.47
     zowel
    0.47
     Vikt
    0.46
     dahil
    0.46
     además
    0.46
     dificultades
    0.46
    Act Density 0.016%

    No Known Activations