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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gage
    -0.07
    .cart
    -0.07
    ozilla
    -0.07
     son
    -0.06
    kontakte
    -0.06
     الفند
    -0.06
     po
    -0.06
     hosp
    -0.06
    뢴
    -0.06
    (Code
    -0.06
    POSITIVE LOGITS
    前述
    0.08
    (that
    0.08
     Ahmed
    0.07
     blackjack
    0.07
    .settings
    0.07
    .Chat
    0.07
     Jays
    0.07
    ●
    0.06
     INTEGER
    0.06
     innings
    0.06
    Act Density 0.038%

    No Known Activations