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

    Neuronpedia

    INDEX
    Explanations

    guides, prompts, and templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maps
    0.46
     details
    0.42
     results
    0.42
     ​​
    0.42
     compare
    0.41
    الت
    0.40
     videos
    0.40
     нажмите
    0.40
     reviews
    0.39
    명
    0.39
    POSITIVE LOGITS
    同學們
    0.41
    欣賞
    0.41
     катего
    0.40
     venced
    0.39
    囑
    0.39
    [-\
    0.39
    0.39
     [-
    0.38
     admired
    0.37
    忿
    0.37
    Act Density 0.001%

    No Known Activations