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

    Neuronpedia

    INDEX
    Explanations

    journal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nel
    -0.08
     Noel
    -0.08
     Rafael
    -0.07
    riel
    -0.07
    cdf
    -0.07
    raf
    -0.07
     image
    -0.07
     Soul
    -0.07
     sail
    -0.07
     emotions
    -0.07
    POSITIVE LOGITS
    174
    0.09
    373
    0.09
    170
    0.09
    972
    0.09
    272
    0.09
    270
    0.09
    75
    0.09
    273
    0.09
    173
    0.08
    171
    0.08
    Act Density 0.125%

    No Known Activations