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

    Neuronpedia

    INDEX
    Explanations

    Sciences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     porcelain
    -0.07
    itian
    -0.06
     UserManager
    -0.06
     Snowden
    -0.06
     progressBar
    -0.06
     waitress
    -0.06
    цями
    -0.06
    rina
    -0.06
     ()↵
    -0.06
     projecting
    -0.06
    POSITIVE LOGITS
    zent
    0.07
    ::::::::
    0.07
    _o
    0.07
    _eth
    0.06
     един
    0.06
     tồn
    0.06
     कई
    0.06
     wenig
    0.06
    日
    0.06
    ACH
    0.06
    Act Density 0.000%

    No Known Activations