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

    Neuronpedia

    INDEX
    Explanations

    light activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    с
    0.79
    ed
    0.75
    y
    0.75
    än
    0.74
    os
    0.72
    asen
    0.69
    ider
    0.68
    ari
    0.66
    asia
    0.65
    yer
    0.65
    POSITIVE LOGITS
    すぐに
    0.75
    󰡔
    0.72
    Pues
    0.70
    ک
    0.67
    사
    0.64
     immediately
    0.64
    ל
    0.64
    つ
    0.63
    キ
    0.63
    ５
    0.63
    Act Density 0.004%

    No Known Activations