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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irket
    -0.06
    Anywhere
    -0.06
     IHttpActionResult
    -0.06
     тоб
    -0.06
    римін
    -0.06
     prelim
    -0.06
     Oklahoma
    -0.06
     finger
    -0.06
     Veranst
    -0.06
    tones
    -0.06
    POSITIVE LOGITS
    orne
    0.07
    elix
    0.07
     biased
    0.07
    _Framework
    0.07
    �
    0.06
     approximate
    0.06
    스
    0.06
     unlocks
    0.06
    489
    0.06
    ์ม
    0.06
    Act Density 0.023%

    No Known Activations