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

    Neuronpedia

    INDEX
    Explanations

    division, calculation, description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ab
    0.38
    Prom
    0.35
     Chun
    0.34
    Portal
    0.34
    Missing
    0.34
    மர
    0.34
     abra
    0.34
     embell
    0.33
     delve
    0.33
     a
    0.33
    POSITIVE LOGITS
     साप
    0.43
    issors
    0.41
    由於
    0.40
    🚻
    0.40
     टास्क
    0.39
    ፨
    0.39
     त्यामुळे
    0.39
     स्या
    0.38
     मिळ
    0.38
    ătoare
    0.38
    Act Density 0.000%

    No Known Activations