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

    Neuronpedia

    INDEX
    Explanations

    }{

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /')
    0.43
    :"))
    0.41
    /")
    0.39
     favoriser
    0.38
    ="))
    0.38
     favour
    0.38
    )"))
    0.37
     favours
    0.36
     }))
    0.36
    辔
    0.36
    POSITIVE LOGITS
    <h5>
    0.82
    </h4>
    0.76
    </h5>
    0.72
    <h4>
    0.70
    <h6>
    0.65
    !}{
    0.56
    }}{\
    0.55
    }}{
    0.49
    }{
    0.47
    "},{"
    0.47
    Act Density 0.001%

    No Known Activations