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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boundary
    -0.07
    	day
    -0.06
     SNP
    -0.06
     Hannity
    -0.06
     Ai
    -0.06
    _CAT
    -0.06
     whites
    -0.06
     Ip
    -0.06
    _Back
    -0.06
     liver
    -0.06
    POSITIVE LOGITS
    lobs
    0.06
     Kenn
    0.06
    alias
    0.06
    asyarak
    0.06
    (↵
    0.06
    .actual
    0.06
     Jerseys
    0.06
     Upgrade
    0.06
    Send
    0.06
    &&(
    0.06
    Act Density 0.039%

    No Known Activations