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

    Neuronpedia

    INDEX
    Explanations

    It

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enumi
    -0.81
    dymyr
    -0.75
     définiti
    -0.75
     feroit
    -0.72
    EnableWeb
    -0.68
     ainfi
    -0.68
     étoient
    -0.66
     pouvoit
    -0.66
     Inet
    -0.65
     varandra
    -0.65
    POSITIVE LOGITS
    <bos>
    1.03
    RegressionTest
    0.68
    <eos>
    0.65
     
    0.58
      
    0.52
     betweenstory
    0.52
     breaking
    0.50
     that
    0.49
     given
    0.49
     in
    0.48
    Act Density 0.062%

    No Known Activations