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

    Neuronpedia

    INDEX
    Explanations

    multiple languages and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …
    0.31
    與
    0.29
     and
    0.28
    ,…
    0.28
    ש
    0.28
    스
    0.28
    </strong>
    0.28
     и
    0.28
    Great
    0.28
    and
    0.27
    POSITIVE LOGITS
     আবারো
    0.35
    stown
    0.29
     antiserum
    0.29
     mortem
    0.29
     appalling
    0.28
    SpawnEntry
    0.27
    FindingsRequest
    0.27
    抿
    0.27
    icolored
    0.27
     rbind
    0.27
    Act Density 0.072%

    No Known Activations