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

    Neuronpedia

    INDEX
    Explanations

    clinical measurements and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite

    technical or scientific terms within medical, academic, or research contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     بشكل
    -1.01
    ➷
    -0.94
    mazoo
    -0.94
    Exeunt
    -0.93
    安徽
    -0.91
    ThemeProvider
    -0.91
     ihnen
    -0.90
     protagonisti
    -0.90
    了
    -0.89
     nedenle
    -0.87
    POSITIVE LOGITS
     this
    1.99
     compared
    1.20
     after
    1.03
    それでも
    1.02
    obut
    1.02
     in
    0.99
    اشتی
    0.93
    ポイントは
    0.92
     at
    0.92
     while
    0.92
    Act Density 0.075%

    No Known Activations