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

    Neuronpedia

    INDEX
    Explanations

    "'s"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :)
    -0.08
    ⏜
    -0.07
     departing
    -0.07
    相比于
    -0.07
    但在
    -0.07
    screens
    -0.07
    bastian
    -0.06
    +p
    -0.06
    ,m
    -0.06
    辩护
    -0.06
    POSITIVE LOGITS
     stalls
    0.07
    Feature
    0.06
    _SPECIAL
    0.06
     Needle
    0.06
    exter
    0.06
     investigación
    0.06
    .rule
    0.06
    rray
    0.06
     gatherings
    0.06
    _integral
    0.06
    Act Density 0.001%

    No Known Activations