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

    Neuronpedia

    INDEX
    Explanations

    explain with context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     സൃഷ്ട
    0.38
     огром
    0.36
     entscheid
    0.35
     mencipt
    0.34
     ដ
    0.33
     เรา
    0.33
     человек
    0.33
    诗人
    0.33
     मल्टीप्लाई
    0.32
    Lorsque
    0.32
    POSITIVE LOGITS
     (
    0.36
    /
    0.36
     signage
    0.35
     legal
    0.35
     যেহেতু
    0.34
     advisable
    0.32
     performed
    0.31
     내용
    0.31
     subject
    0.31
     indicated
    0.31
    Act Density 0.453%

    No Known Activations