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

    Neuronpedia

    INDEX
    Explanations

    one of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clockRadius
    0.46
    禟
    0.45
     ڈیز
    0.42
    OFFSET
    0.42
     stockno
    0.41
     OFFSET
    0.41
     températures
    0.40
     utilizzando
    0.40
     paraît
    0.40
    Datasets
    0.40
    POSITIVE LOGITS
     najwięks
    0.59
     key
    0.59
     가장
    0.58
     part
    0.55
     крупней
    0.53
     hallmark
    0.52
     biggest
    0.51
     найбіль
    0.48
     best
    0.48
     one
    0.47
    Act Density 0.005%

    No Known Activations