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

    Neuronpedia

    INDEX
    Explanations

    combining keywords or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initState
    0.88
    InitFlag
    0.83
     trailed
    0.81
     initialization
    0.79
     feedstock
    0.79
    猗
    0.77
    ensuremath
    0.76
    IZING
    0.75
     caramelized
    0.75
     playable
    0.75
    POSITIVE LOGITS
    ri
    0.70
    it
    0.69
    ot
    0.69
    kei
    0.69
     stren
    0.68
    hasil
    0.68
    ins
    0.67
    i
    0.67
    ademie
    0.66
    od
    0.65
    Act Density 0.000%

    No Known Activations