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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    heel
    -0.07
     contenders
    -0.07
    ğen
    -0.07
     家
    -0.07
     Conce
    -0.06
    бас
    -0.06
     smooth
    -0.06
    checkpoint
    -0.06
    .imgur
    -0.06
     breathtaking
    -0.06
    POSITIVE LOGITS
     uses
    0.07
     uvol
    0.06
     use
    0.06
     utilized
    0.06
     incorpor
    0.06
    (org
    0.06
     于
    0.06
    	label
    0.06
     using
    0.06
     utilize
    0.06
    Act Density 0.047%

    No Known Activations