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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    mathematical problems or expressions, particularly those related to factors and divisors.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    2
    -0.10
    4
    -0.09
    8
    -0.07
     four
    -0.07
    112
    -0.07
    14
    -0.06
     Lee
    -0.06
     eight
    -0.06
     six
    -0.06
    aising
    -0.06
    POSITIVE LOGITS
    .Collections
    0.07
    =edge
    0.07
     �
    0.07
    reas
    0.06
     неск
    0.06
    .jboss
    0.06
    ↵      ↵
    0.06
    ικο
    0.06
     ува
    0.06
     υπο
    0.06
    Act Density 0.116%

    No Known Activations