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

    Neuronpedia

    INDEX
    Explanations

    Deep Dive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deput
    0.38
     embroiled
    0.37
    wide
    0.35
    chairman
    0.33
     rodzin
    0.32
     ଦ
    0.32
    ﺪ
    0.32
    ego
    0.31
     Est
    0.31
    apprent
    0.31
    POSITIVE LOGITS
    /
    0.39
    нды
    0.37
    จน
    0.36
    CEPTION
    0.35
    ANDS
    0.34
    י
    0.33
    니스
    0.32
    ны
    0.31
    ANDE
    0.31
    ADOW
    0.31
    Act Density 0.048%

    No Known Activations