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

    Neuronpedia

    INDEX
    Explanations

    // comments and code actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵↵↵
    0.51
    ↵↵↵
    0.46
     --
    0.44
    可以
    0.44
     注意
    0.44
     see
    0.42
     olabilir
    0.42
     可以
    0.41
     See
    0.41
    0.41
    POSITIVE LOGITS
    ianSpace
    0.43
    abayashi
    0.41
    othe
    0.40
    চরা
    0.40
     grammat
    0.40
     elucid
    0.39
    ಕಾಶ
    0.39
    сної
    0.39
     theorem
    0.39
    ΡΑ
    0.39
    Act Density 0.059%

    No Known Activations