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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fragen
    -0.08
     refill
    -0.07
     graduates
    -0.06
    尋
    -0.06
    .students
    -0.06
     helping
    -0.06
     CONTEXT
    -0.06
    control
    -0.06
    仰
    -0.05
     Hunters
    -0.05
    POSITIVE LOGITS
    __,↵
    0.07
    ugeot
    0.07
    .linkLabel
    0.07
     Keywords
    0.07
    WebKit
    0.07
    cov
    0.06
    ={{↵
    0.06
     agon
    0.06
     Mn
    0.06
     __________________
    0.06
    Act Density 0.153%

    No Known Activations