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

    Neuronpedia

    INDEX
    Explanations

    entity toward or regarding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    id
    0.48
     starred
    0.42
    of
    0.41
    uv
    0.41
    atoti
    0.40
     thinks
    0.40
    anya
    0.40
    uca
    0.39
    at
    0.39
     hails
    0.39
    POSITIVE LOGITS
     تجاه
    0.61
     privind
    0.50
     والتي
    0.48
     щодо
    0.44
     بشأن
    0.43
     dotyczące
    0.43
     terhadap
    0.42
     جميعا
    0.42
     cuánto
    0.41
     czyli
    0.40
    Act Density 0.087%

    No Known Activations