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

    Neuronpedia

    INDEX
    Explanations

    history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dividing
    -0.07
     walls
    -0.07
     department
    -0.07
     premature
    -0.06
     praised
    -0.06
     sean
    -0.06
     sts
    -0.06
     clicking
    -0.06
     business
    -0.06
     перен
    -0.06
    POSITIVE LOGITS
    ói
    0.07
    .”
    0.06
    탁
    0.06
    -lnd
    0.06
    ，全
    0.06
    roman
    0.06
    Every
    0.06
    exter
    0.06
    (any
    0.06
    .Roll
    0.06
    Act Density 0.001%

    No Known Activations