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

    Neuronpedia

    INDEX
    Explanations

    use, special, usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    誰
    0.42
     sequestration
    0.40
    음을
    0.40
     жизни
    0.39
     возможностей
    0.38
    疇
    0.37
     foo
    0.36
    指南
    0.36
    чак
    0.36
    どこ
    0.36
    POSITIVE LOGITS
     specially
    0.42
     kullanılır
    0.42
     certaine
    0.40
     especial
    0.39
     gunakan
    0.39
     utilisons
    0.39
    kb
    0.38
     membre
    0.38
     cabang
    0.37
     ayrıca
    0.37
    Act Density 0.001%

    No Known Activations