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

    Neuronpedia

    INDEX
    Explanations

    programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vaše
    0.45
    -'].
    0.44
     என்பவர்
    0.43
    ისა
    0.42
     이상의
    0.42
    으로서
    0.42
     آنچه
    0.42
    яў
    0.40
    Dieser
    0.40
    urier
    0.39
    POSITIVE LOGITS
    ↵
    0.72
    ‬
    0.56
     using
    0.55
     =)
    0.47
     👇
    0.46
     before
    0.46
     avoiding
    0.46
     -->
    0.45
     without
    0.45
     */}
    0.45
    Act Density 0.035%

    No Known Activations