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

    Neuronpedia

    INDEX
    Explanations

    low values, closer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    最大
    0.44
    maximum
    0.44
     максима
    0.44
    最多
    0.43
     synchronization
    0.42
    同步
    0.41
    Synchronization
    0.41
    synchron
    0.40
    znych
    0.40
    limited
    0.40
    POSITIVE LOGITS
     closer
    0.65
     값이
    0.61
     values
    0.60
     값을
    0.55
     nearer
    0.54
    값을
    0.54
     값
    0.54
    값
    0.53
    值
    0.53
     낮
    0.52
    Act Density 0.008%

    No Known Activations