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

    Neuronpedia

    INDEX
    Explanations

    names followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     luminosity
    0.34
     but
    0.32
    ↵
    0.32
    ！
    0.32
     indes
    0.31
     brightness
    0.30
     radiance
    0.29
    }$
    0.29
     parameters
    0.29
     dign
    0.29
    POSITIVE LOGITS
     مزاج
    0.36
     ছিলাম
    0.34
    主义
    0.33
     Downtown
    0.33
     بشأن
    0.32
     درباره
    0.31
    簹
    0.31
     കേന്ദ്ര
    0.30
    igrant
    0.30
     страте
    0.29
    Act Density 0.000%

    No Known Activations