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

    Neuronpedia

    INDEX
    Explanations

    disadvantage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    овід
    -0.07
    ================================================
    -0.07
    oid
    -0.07
    edith
    -0.07
     Zac
    -0.06
     injection
    -0.06
    kinson
    -0.06
     отвеч
    -0.06
    aporation
    -0.06
    URY
    -0.06
    POSITIVE LOGITS
     Lockheed
    0.07
     kaufen
    0.06
     كبيرة
    0.06
    vk
    0.06
     CDC
    0.06
    _invoice
    0.06
     applicable
    0.06
     Định
    0.06
     تغ
    0.06
    (curl
    0.06
    Act Density 0.007%

    No Known Activations