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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pisode
    -0.08
     goodbye
    -0.08
    announce
    -0.07
     있도록
    -0.07
     Coast
    -0.07
     gara
    -0.07
    -0.07
     beginnings
    -0.07
     diner
    -0.07
     Murder
    -0.07
    POSITIVE LOGITS
     contributions
    0.10
    综合
    0.10
     uncertainties
    0.10
     contribut
    0.09
     noise
    0.09
    Gaussian
    0.09
    RAND
    0.09
     contributing
    0.09
     Noise
    0.09
    Noise
    0.09
    Act Density 0.006%
    No Known Activations