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

    Neuronpedia

    INDEX
    Explanations

    Date

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     current
    -0.08
     twisted
    -0.07
    人們
    -0.07
     Close
    -0.07
    Thor
    -0.07
    Next
    -0.07
    wall
    -0.06
     Myers
    -0.06
    operation
    -0.06
     Qing
    -0.06
    POSITIVE LOGITS
    .fetchone
    0.07
    Navig
    0.07
     Shapiro
    0.07
    𐤂
    0.07
     разных
    0.07
    CEE
    0.07
    푹
    0.07
     חדש
    0.07
    🏗
    0.07
    潾
    0.07
    Act Density 0.021%

    No Known Activations