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

    Neuronpedia

    INDEX
    Explanations

    initial full, NET Framework, window title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sacrific
    0.43
     Sacrifice
    0.43
     البد
    0.39
    piel
    0.39
    少的
    0.39
    ဂျ
    0.38
    選項
    0.38
    étr
    0.38
     Ters
    0.38
    电池
    0.38
    POSITIVE LOGITS
     analyzing
    0.42
     Analyze
    0.40
    DummyView
    0.39
     charting
    0.39
    ความคิด
    0.38
    Analyze
    0.38
     иногда
    0.38
     opinions
    0.38
    flo
    0.37
     querido
    0.37
    Act Density 0.000%

    No Known Activations