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

    Neuronpedia

    INDEX
    Explanations

    describing symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pering
    0.43
     conundrum
    0.42
     benevolence
    0.41
     bew
    0.40
     selfishness
    0.40
     disconcert
    0.39
    すら
    0.39
     benevolent
    0.39
     sting
    0.38
     chagrin
    0.38
    POSITIVE LOGITS
    ittu
    0.40
    玽
    0.39
    症状
    0.38
     jakieś
    0.37
     симпто
    0.37
    认识
    0.37
     accompanied
    0.36
    extérieur
    0.36
    friger
    0.36
    液体
    0.36
    Act Density 0.042%

    No Known Activations