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

    Neuronpedia

    INDEX
    Explanations

    old-fashioned or old days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘯
    1.20
    𝘵
    1.17
    ğin
    1.10
    𝘶
    1.07
    𝘱
    1.07
     gridSize
    1.05
    נות
    1.04
    𝘷
    1.02
     wissen
    1.00
    𝘣
    1.00
    POSITIVE LOGITS
     noqa
    1.36
    Proposition
    1.28
    नैतिक
    1.16
    memset
    1.15
    circledR
    1.14
    )}+
    1.12
    پیش
    1.12
    ید
    1.09
    endif
    1.09
     "")
    1.08
    Act Density 0.001%

    No Known Activations