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

    Neuronpedia

    INDEX
    Explanations

    stylistic and narrative techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    worldwide
    0.53
     realities
    0.48
     worded
    0.48
     worldwide
    0.46
     depicted
    0.46
     directories
    0.46
     depicts
    0.46
     ಪರಿಸ
    0.46
    terminated
    0.45
     optimistic
    0.44
    POSITIVE LOGITS
     stylistic
    0.75
    技巧
    0.74
     subtlety
    0.73
     Techniques
    0.72
     technique
    0.71
     techniques
    0.70
     compositional
    0.70
    手法
    0.69
     эсте
    0.69
     Technique
    0.68
    Act Density 0.010%

    No Known Activations