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

    Neuronpedia

    INDEX
    Explanations

    ognito

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    משך
    -0.07
    אר
    -0.07
     সংশ
    -0.07
     Lion
    -0.07
     leves
    -0.07
     уш
    -0.07
     transportation
    -0.07
     সম্ভ
    -0.07
    Lf
    -0.07
     Crescent
    -0.07
    POSITIVE LOGITS
     Variant
    0.09
    Variant
    0.08
    ,password
    0.08
    (UUID
    0.08
    .variant
    0.08
    iché
    0.08
     sunglasses
    0.08
    unnar
    0.07
     variant
    0.07
     режиме
    0.07
    Act Density 0.002%

    No Known Activations