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

    Neuronpedia

    INDEX
    Explanations

    meaning, true, often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sample
    0.45
    sick
    0.45
    0.45
    kens
    0.44
    acetic
    0.43
    Butyl
    0.43
    foto
    0.43
     দেখেন
    0.43
     measles
    0.43
     chrysanthemum
    0.43
    POSITIVE LOGITS
     OnTrigger
    0.44
     finalidad
    0.44
    лната
    0.43
    倾
    0.42
    天堂
    0.41
     మీద
    0.41
    uru
    0.40
     مقصد
    0.40
    节奏
    0.39
    ρίες
    0.39
    Act Density 0.009%

    No Known Activations