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

    Neuronpedia

    INDEX
    Explanations

    Ellipses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disap
    -0.07
     delighted
    -0.07
     nitelik
    -0.06
    tright
    -0.06
    Markdown
    -0.06
     Anal
    -0.06
     dear
    -0.06
     Ded
    -0.06
     files
    -0.06
    mland
    -0.06
    POSITIVE LOGITS
    ynamo
    0.06
     POT
    0.06
     ….
    0.06
     …
    0.06
     Watching
    0.06
     Pfizer
    0.06
    roj
    0.06
     garner
    0.06
    OTE
    0.06
     [...]
    0.06
    Act Density 0.013%

    No Known Activations