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

    Neuronpedia

    INDEX
    Explanations

    code formatting characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    گی
    -0.08
    ائج
    -0.06
    vý
    -0.06
     Grande
    -0.06
    affer
    -0.06
    前的
    -0.06
    
    -0.06
    umuz
    -0.06
    eczy
    -0.06
    ilar
    -0.06
    POSITIVE LOGITS
     Ref
    0.07
     Episodes
    0.07
    cho
    0.07
    gard
    0.06
     sim
    0.06
    <Element
    0.06
    curr
    0.06
     �
    0.06
     frustrating
    0.06
     вост
    0.06
    Act Density 0.013%

    No Known Activations