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

    Neuronpedia

    INDEX
    Explanations

    medical advice disclaimer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ИК
    0.39
    AWSJavaScriptSDK
    0.38
     фикси
    0.38
    loten
    0.38
    )،
    0.38
     бол
    0.37
     hebdom
    0.37
     كلهم
    0.37
    Таким
    0.36
    ७
    0.36
    POSITIVE LOGITS
     executions
    0.38
     gyms
    0.36
     transformations
    0.36
     transformation
    0.36
     to
    0.35
     mobility
    0.35
     practices
    0.34
     tribulations
    0.34
     haircuts
    0.34
     warping
    0.33
    Act Density 0.008%

    No Known Activations