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

    Neuronpedia

    INDEX
    Explanations

    bold markers and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.91
    ’
    0.83
    }^{
    0.78
    된
    0.75
     hindrance
    0.72
    𝐀
    0.68
    LY
    0.68
    }}{\
    0.67
     remarkable
    0.63
    ERO
    0.63
    POSITIVE LOGITS
    tı
    0.79
     لوگوں
    0.75
    óloga
    0.74
    りで
    0.74
    adis
    0.71
     airfield
    0.71
    :'',
    0.68
     людьми
    0.68
    ChooseCharacter
    0.68
    哮
    0.68
    Act Density 0.305%

    No Known Activations