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

    Neuronpedia

    INDEX
    Explanations

    explain why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    0.47
     statist
    0.46
    f
    0.46
    am
    0.45
     Sam
    0.44
    ד
    0.44
     incentivize
    0.44
    financ
    0.43
    ח
    0.43
    trag
    0.42
    POSITIVE LOGITS
    ین
    0.54
     बाद
    0.46
     ລັບ
    0.45
    岕
    0.45
     দর্শকের
    0.44
     cometido
    0.44
     इस
    0.43
     हर्
    0.43
    没有什么
    0.42
     Mujeres
    0.42
    Act Density 0.008%

    No Known Activations