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

    Neuronpedia

    INDEX
    Explanations

    round

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     municip
    -0.07
     maple
    -0.07
    _tE
    -0.07
    ximo
    -0.06
     Regiment
    -0.06
    !)↵↵
    -0.06
     dere
    -0.06
     Доб
    -0.06
    Ε
    -0.06
    щество
    -0.06
    POSITIVE LOGITS
     sac
    0.07
    logged
    0.07
    .bits
    0.06
    .Columns
    0.06
    .k
    0.06
    artic
    0.06
     beginnings
    0.06
     halten
    0.06
    ・━・━・━・━
    0.06
    borrow
    0.06
    Act Density 0.041%

    No Known Activations