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

    Neuronpedia

    INDEX
    Explanations

    Conservative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /domain
    -0.07
     yogurt
    -0.07
    ап
    -0.06
    ascending
    -0.06
     buds
    -0.06
     boots
    -0.06
    .RemoveAt
    -0.06
    neighbor
    -0.06
     Ferdinand
    -0.06
    querque
    -0.06
    POSITIVE LOGITS
     Tories
    0.08
     Tory
    0.07
    809
    0.06
     ομά
    0.06
    ;;;;
    0.06
    _Default
    0.06
     Bul
    0.06
     경북
    0.06
     spoilers
    0.06
    .Center
    0.06
    Act Density 0.004%

    No Known Activations