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

    Neuronpedia

    INDEX
    Explanations

    Java/Spring code and questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sophie
    -0.08
     TUR
    -0.07
    abli
    -0.07
     esqu
    -0.07
     cruising
    -0.07
    -cu
    -0.07
     yaxshi
    -0.07
     aer
    -0.07
     futuristic
    -0.07
    loopt
    -0.07
    POSITIVE LOGITS
     wort
    0.10
    beans
    0.09
     beans
    0.09
    ikar
    0.08
     neurotrans
    0.08
     ελλην
    0.08
     rocking
    0.08
    warn
    0.08
     repress
    0.08
     serotonin
    0.08
    Act Density 0.004%

    No Known Activations