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

    Neuronpedia

    INDEX
    Explanations

    part or phase number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CHAPTER
    0.38
     rep
    0.38
    chapters
    0.37
     chl
    0.37
    Chapters
    0.36
    RETURN
    0.35
    ထား
    0.35
     chapters
    0.34
     chlorophyll
    0.34
    chh
    0.34
    POSITIVE LOGITS
    Phase
    0.67
     phase
    0.64
     Phase
    0.60
     fase
    0.56
     PHASE
    0.53
    phase
    0.49
    阶段
    0.48
     المرحلة
    0.46
     Fase
    0.44
    Stage
    0.42
    Act Density 0.005%

    No Known Activations