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

    Neuronpedia

    INDEX
    Explanations

    isolation of new original transformers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CSI
    0.77
     Iranian
    0.73
     depan
    0.72
    ۰
    0.72
     Brazilian
    0.72
     halting
    0.71
     manzanas
    0.70
     Sustainable
    0.70
     Chile
    0.70
     particularly
    0.69
    POSITIVE LOGITS
     jobSearch
    0.77
    名は
    0.73
     lediglich
    0.73
    েন্দ্রলাল
    0.73
    rored
    0.72
     sorgen
    0.72
    mx
    0.70
     vorstellen
    0.70
    naio
    0.70
    no
    0.69
    Act Density 0.001%

    No Known Activations