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

    Neuronpedia

    INDEX
    Explanations

    System

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quizzes
    -0.06
     Numbers
    -0.06
     quilt
    -0.06
    ・マ
    -0.06
    -metadata
    -0.06
    flare
    -0.06
     acrylic
    -0.06
     لف
    -0.06
     Bak
    -0.06
     Across
    -0.06
    POSITIVE LOGITS
    ]*(
    0.08
     www
    0.07
    oulouse
    0.07
    _Str
    0.06
    iembre
    0.06
    历史
    0.06
    _Mode
    0.06
    oving
    0.06
    變
    0.06
    상
    0.06
    Act Density 0.031%

    No Known Activations