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

    Neuronpedia

    INDEX
    Explanations

    writing prompts for content types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    优先级
    0.78
     खबरों
    0.77
     중요
    0.74
    従来
    0.73
     envolv
    0.72
    ળ
    0.71
    未知
    0.71
    Specificity
    0.70
    强大
    0.70
    常に
    0.70
    POSITIVE LOGITS
     featuring
    1.80
     depicting
    1.78
     titled
    1.75
     written
    1.72
     entitled
    1.64
     showcasing
    1.51
     penned
    1.50
     starring
    1.47
     commemorating
    1.43
     detailing
    1.39
    Act Density 1.254%

    No Known Activations