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

    Neuronpedia

    INDEX
    Explanations

    initially sweet, weak, or lower

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ifdef
    0.48
    ua
    0.45
    }$.
    0.45
    ould
    0.44
    अमेर
    0.44
    अन्य
    0.44
    olot
    0.44
    system
    0.43
    षे
    0.43
    ا۔
    0.43
    POSITIVE LOGITS
     phúc
    0.51
     geoLocation
    0.51
     shirtless
    0.50
    すすめ
    0.48
     genieten
    0.48
     spectacle
    0.47
     favorite
    0.46
     genießen
    0.46
     stargazerCount
    0.46
     speechless
    0.46
    Act Density 0.007%

    No Known Activations