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

    Neuronpedia

    INDEX
    Explanations

    URLs and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reden
    0.58
    总结
    0.53
     nochmal
    0.48
     Versorgung
    0.48
    沌
    0.48
     indices
    0.47
     আবার
    0.47
     scaling
    0.47
     vortex
    0.47
     다시
    0.46
    POSITIVE LOGITS
    Specifically
    0.71
     Specifically
    0.67
    ulièrement
    0.65
    </sub>
    0.63
    </sup>
    0.61
    boats
    0.60
    posted
    0.60
    loir
    0.59
    Oh
    0.58
     Namely
    0.58
    Act Density 0.140%

    No Known Activations