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

    Neuronpedia

    INDEX
    Explanations

    additional or extra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を目指
    0.72
     駅
    0.69
    ventud
    0.64
     ponctuées
    0.64
     murky
    0.63
     sustancias
    0.63
     อัน
    0.62
    複雜
    0.62
     ormai
    0.61
    复杂的
    0.60
    POSITIVE LOGITS
     additional
    4.15
     extra
    4.09
    additional
    3.83
    Additional
    3.82
    额外的
    3.73
     Additional
    3.71
    额外
    3.66
     дополни
    3.60
    Extra
    3.52
     zusätzliche
    3.52
    Act Density 0.290%

    No Known Activations