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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Starting
    -0.07
     //}↵
    -0.06
    <button
    -0.06
     protocols
    -0.06
     が
    -0.06
    (search
    -0.06
    `,
    -0.06
    On
    -0.06
     "&
    -0.06
     Chains
    -0.06
    POSITIVE LOGITS
     Olympia
    0.07
    modification
    0.07
    football
    0.07
     цел
    0.06
    �
    0.06
     ance
    0.06
     drafting
    0.06
    swick
    0.06
    maids
    0.06
    рис
    0.06
    Act Density 0.005%

    No Known Activations