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

    Neuronpedia

    INDEX
    Explanations

    vertical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wagner
    -0.08
     Contr
    -0.07
    𝄅
    -0.07
     puzz
    -0.07
     WaitFor
    -0.07
     Firmware
    -0.07
    _fixture
    -0.07
    note
    -0.07
    	BIT
    -0.06
    听完
    -0.06
    POSITIVE LOGITS
     destroyed
    0.07
    "};↵↵
    0.07
    离
    0.07
    محاكم
    0.07
     squads
    0.07
     `.
    0.07
    Pooling
    0.07
    -effects
    0.07
    眼界
    0.06
    rá
    0.06
    Act Density 0.001%

    No Known Activations