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

    Neuronpedia

    INDEX
    Explanations

    llll

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olen
    -0.07
     ово
    -0.07
    .NEW
    -0.07
    uke
    -0.07
     Hew
    -0.07
     obten
    -0.06
    .mag
    -0.06
    #####↵
    -0.06
    urchase
    -0.06
    uvo
    -0.06
    POSITIVE LOGITS
    と
    0.07
    omi
    0.06
     Council
    0.06
    Council
    0.06
    학
    0.06
    Clipboard
    0.06
     fundamentals
    0.06
    branch
    0.06
    ち
    0.06
    lickr
    0.06
    Act Density 0.001%

    No Known Activations