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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     belts
    -0.07
     ENTITY
    -0.07
    (create
    -0.07
    _wheel
    -0.07
     approximate
    -0.07
    lesi
    -0.06
    れた
    -0.06
     vivo
    -0.06
    IELDS
    -0.06
     Cultural
    -0.06
    POSITIVE LOGITS
    yang
    0.06
     SAY
    0.06
    /******/
    0.06
    [position
    0.06
     ор
    0.06
     착
    0.06
     chuẩn
    0.06
    "]=>
    0.06
    跨
    0.06
     wollte
    0.06
    Act Density 0.055%

    No Known Activations