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

    Neuronpedia

    INDEX
    Explanations

    Angular CLI commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఉ
    0.46
     anex
    0.44
     swaps
    0.43
     Swap
    0.39
    ఉ
    0.39
     tanggung
    0.39
    حدد
    0.38
    ធម្ម
    0.38
     swap
    0.38
    وع
    0.38
    POSITIVE LOGITS
     CLI
    0.76
    CLI
    0.70
    sche
    0.66
     sche
    0.63
    devkit
    0.63
    Sche
    0.62
    cli
    0.60
     Sche
    0.58
     Schematic
    0.55
     cli
    0.55
    Act Density 0.006%

    No Known Activations