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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heats
    -0.07
     hơn
    -0.07
    metatable
    -0.06
     Completion
    -0.06
     Μετα
    -0.06
    .DataTable
    -0.06
    _lineno
    -0.06
     flawless
    -0.06
    中文字幕
    -0.06
    ━━━━━━━━━━━━━━━━
    -0.06
    POSITIVE LOGITS
    ])↵↵
    0.07
    0.06
    ]:↵↵
    0.06
    sob
    0.06
    (Build
    0.06
     desc
    0.06
     ************************************************************************
    0.06
    وند
    0.06
    ross
    0.06
    jab
    0.06
    Act Density 0.086%

    No Known Activations