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

    Neuronpedia

    INDEX
    Explanations

    defined

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conformity
    -0.08
     curtain
    -0.07
     adicion
    -0.07
     scared
    -0.07
    领导者
    -0.07
    _um
    -0.07
     bidder
    -0.07
    罶
    -0.07
     baptized
    -0.07
    📎
    -0.07
    POSITIVE LOGITS
    .sessions
    0.07
     RM
    0.07
     đã
    0.07
    inct
    0.07
     Sunday
    0.07
    产
    0.06
    PlainOldData
    0.06
     çalışmaları
    0.06
     судеб
    0.06
    subsection
    0.06
    Act Density 0.001%

    No Known Activations