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

    Neuronpedia

    INDEX
    Explanations

    puzzles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Boss
    -0.07
     Disconnect
    -0.07
    .commands
    -0.07
     '@/
    -0.07
     prioritize
    -0.07
     postings
    -0.06
    .broadcast
    -0.06
    /twitter
    -0.06
     responsibility
    -0.06
    connected
    -0.06
    POSITIVE LOGITS
    Href
    0.07
     smě
    0.06
    oeff
    0.06
     악
    0.06
    career
    0.06
    lena
    0.06
    edb
    0.06
    urable
    0.06
    &&!
    0.06
    esium
    0.06
    Act Density 0.006%

    No Known Activations