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

    Neuronpedia

    INDEX
    Explanations

    person, specific, spiritual, they, most

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     செயல்
    0.43
    㕕
    0.43
    ادو
    0.42
    𝕕
    0.42
     limitar
    0.42
     disposição
    0.42
    দো
    0.41
    تباينه
    0.40
    wami
    0.40
    ками
    0.39
    POSITIVE LOGITS
     тебя
    0.51
    0.51
     from
    0.45
    0
    0.45
    itary
    0.44
     вспо
    0.44
     вокруг
    0.43
    ?
    0.42
     Membuat
    0.42
     around
    0.42
    Act Density 0.002%

    No Known Activations