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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Empire
    -0.07
     gained
    -0.07
     واس
    -0.06
    -food
    -0.06
     athletics
    -0.06
    )>=
    -0.06
    NOTE
    -0.06
    Prob
    -0.06
     persec
    -0.06
     Locked
    -0.06
    POSITIVE LOGITS
    Showing
    0.07
    нять
    0.07
     našeho
    0.07
     (:
    0.06
    weakSelf
    0.06
    .trigger
    0.06
    )",
↵
    0.06
    (ir
    0.06
     <?=$
    0.06
    itou
    0.06
    Act Density 0.075%

    No Known Activations