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

    Neuronpedia

    INDEX
    Explanations

    python imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ים
    0.42
    imide
    0.37
    鯰
    0.35
    raction
    0.34
    صميم
    0.34
     प्रवक्ता
    0.34
    لف
    0.33
    pertension
    0.33
    ptime
    0.33
    iphatic
    0.33
    POSITIVE LOGITS
     señales
    0.41
     eroded
    0.40
     हाला
    0.39
     diagrams
    0.39
     yielded
    0.38
     signals
    0.38
    𝚜
    0.37
     walaupun
    0.37
     Publish
    0.36
     crowned
    0.36
    Act Density 0.001%

    No Known Activations