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

    Neuronpedia

    INDEX
    Explanations

    progress and load status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    绺
    0.40
    Cómo
    0.39
    amsmath
    0.39
     পন্থা
    0.38
    olischen
    0.38
     arasındaki
    0.37
    鸪
    0.37
    鷸
    0.37
    颏
    0.36
     Cómo
    0.36
    POSITIVE LOGITS
     progress
    0.45
    progress
    0.44
    Progress
    0.42
     Progress
    0.41
     loads
    0.40
    load
    0.39
    uptime
    0.37
     (%)
    0.37
    loads
    0.36
     time
    0.35
    Act Density 0.000%

    No Known Activations