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

    Neuronpedia

    INDEX
    Explanations

    Isabella

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    coln
    0.69
     Peso
    0.67
     Apart
    0.66
    Heinrich
    0.66
     Limit
    0.66
     Veil
    0.66
    াবী
    0.66
    ުގައި
    0.65
    Peso
    0.65
    Apart
    0.65
    POSITIVE LOGITS
    mentare
    0.74
     opiniones
    0.73
    hidupan
    0.72
     completely
    0.71
    completely
    0.69
    完全に
    0.69
    俸
    0.69
    ylabel
    0.69
     zcela
    0.67
    まったく
    0.67
    Act Density 0.002%

    No Known Activations