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

    Neuronpedia

    INDEX
    Explanations

    dependencies and repositories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NSMakeRange
    0.45
    🚱
    0.43
    現実
    0.40
    Sexual
    0.40
    願意
    0.40
    🈯
    0.40
    コス
    0.40
    ስቃ
    0.40
    唥
    0.40
    髡
    0.40
    POSITIVE LOGITS
    dependencies
    0.65
     repositories
    0.61
     dependencies
    0.60
     dependency
    0.60
    repositories
    0.58
     task
    0.57
    sources
    0.57
    dependency
    0.56
     sources
    0.55
     source
    0.54
    Act Density 0.005%

    No Known Activations