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

    Neuronpedia

    INDEX
    Explanations

    /etc/ files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    路径
    0.47
    Users
    0.45
     Pathways
    0.44
    用户的
    0.43
    ทาง
    0.42
    প্যাথ
    0.40
    ~$
    0.38
     supon
    0.38
     plutôt
    0.38
    AbsolutePath
    0.38
    POSITIVE LOGITS
     Blade
    0.40
    Else
    0.39
     devoir
    0.39
    Mechanical
    0.39
     MECHANICAL
    0.38
    Volvo
    0.38
     ADMIN
    0.37
     Rosenberg
    0.37
    වන
    0.36
    Blade
    0.36
    Act Density 0.005%

    No Known Activations