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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mtx
    -0.07
    矍
    -0.07
    (EXPR
    -0.07
     CMS
    -0.07
    ueling
    -0.06
     ADDR
    -0.06
    젓
    -0.06
    (level
    -0.06
    <context
    -0.06
    卤
    -0.06
    POSITIVE LOGITS
     behaviour
    0.07
    见到
    0.07
    Precio
    0.06
    Interest
    0.06
    国债
    0.06
    UILDER
    0.06
    FORE
    0.06
    뷗
    0.06
     drawn
    0.06
    غال
    0.06
    Act Density 0.001%

    No Known Activations