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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric values—especially floating-point numbers and other metrics with decimal points.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     embeddings
    -0.07
     Collision
    -0.07
    dığ
    -0.06
    ्र
    -0.06
    AccessToken
    -0.06
     Suzanne
    -0.06
                ↵↵
    -0.06
    [child
    -0.06
     derives
    -0.06
    FAST
    -0.06
    POSITIVE LOGITS
     reinforce
    0.07
    遊
    0.06
    ocket
    0.06
     SignUp
    0.06
     dealership
    0.06
    ηρε
    0.06
    憶
    0.06
    ูตร
    0.06
    placed
    0.06
    forder
    0.06
    Act Density 0.165%

    No Known Activations