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

    Neuronpedia

    INDEX
    Explanations

    code with parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᄌ
    0.49
    您
    0.46
    珹
    0.46
    亽
    0.46
    ᄅ
    0.46
    𝑔
    0.46
    忔
    0.46
    瑯
    0.44
    琙
    0.44
    秆
    0.43
    POSITIVE LOGITS
     twilight
    0.50
     prevalent
    0.47
     yet
    0.46
     Kamala
    0.46
     cheerful
    0.44
     harbours
    0.44
     cinque
    0.44
     café
    0.43
     five
    0.43
     yaw
    0.43
    Act Density 0.001%

    No Known Activations