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

    Neuronpedia

    INDEX
    Explanations

    group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    0.39
     അല്ല
    0.38
     ObjData
    0.36
     душа
    0.36
     Szer
    0.36
    丰富的
    0.35
     mực
    0.35
    Hr
    0.35
    SHADER
    0.35
    获得的
    0.34
    POSITIVE LOGITS
    цов
    0.41
    regated
    0.40
    EDE
    0.39
     hỗn
    0.39
    enzo
    0.39
    Playback
    0.38
     高級
    0.38
    ex
    0.37
    ць
    0.37
    Never
    0.37
    Act Density 0.000%

    No Known Activations