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

    Neuronpedia

    INDEX
    Explanations

    search for suspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brasil
    0.66
    ucaly
    0.65
    Supplemental
    0.65
     Brot
    0.60
    申请
    0.60
    Protein
    0.58
    異なる
    0.58
     Architectural
    0.58
     архитек
    0.57
    Incremental
    0.57
    POSITIVE LOGITS
     Entered
    0.58
     FBI
    0.58
    ोली
    0.54
     lineup
    0.53
    愤怒
    0.53
     crackdown
    0.53
     plunged
    0.52
    배
    0.52
     venge
    0.52
     enraged
    0.51
    Act Density 0.000%

    No Known Activations