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

    Neuronpedia

    INDEX
    Explanations

    H

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Crystal
    -0.07
    燃
    -0.06
    Absolutely
    -0.06
     Start
    -0.06
     retal
    -0.06
     Frequ
    -0.06
     Repair
    -0.06
     sequences
    -0.06
     Develop
    -0.06
     handmade
    -0.06
    POSITIVE LOGITS
    -desc
    0.07
    .Entry
    0.07
    
    0.07
     chce
    0.07
    heets
    0.07
    endency
    0.06
    slaught
    0.06
    (exc
    0.06
    IMATION
    0.06
    ologna
    0.06
    Act Density 0.081%

    No Known Activations