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

    Neuronpedia

    INDEX
    Explanations

    small-cap stocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    泗
    0.54
     Кі
    0.53
    一定
    0.51
     കെ
    0.51
    紧张
    0.51
    エアコン
    0.50
    溘
    0.50
    hältnis
    0.50
    싱
    0.49
    ություն
    0.48
    POSITIVE LOGITS
     for
    0.61
     omitted
    0.61
    ig
    0.60
     devoured
    0.58
     chases
    0.57
    al
    0.56
    d
    0.56
    ิ
    0.55
    es
    0.55
     synced
    0.55
    Act Density 0.003%

    No Known Activations