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

    Neuronpedia

    INDEX
    Explanations

    Join Us

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    屋外
    0.52
    ный
    0.46
    也就是
    0.46
    崠
    0.46
     длина
    0.46
    走出
    0.46
    垕
    0.46
    棪
    0.46
    製造
    0.46
    ฟ
    0.46
    POSITIVE LOGITS
    limit
    0.52
     saling
    0.47
     complications
    0.47
    varepsilon
    0.46
     concomitant
    0.45
     anv
    0.45
     agro
    0.45
     caret
    0.44
    care
    0.44
     limit
    0.44
    Act Density 0.010%

    No Known Activations