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

    Neuronpedia

    INDEX
    Explanations

    Triangles

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals (especially floating‐point constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     novel
    -0.08
    �
    -0.08
     Waters
    -0.07
     sắt
    -0.07
     origins
    -0.07
     Cincinnati
    -0.07
     endings
    -0.07
    talk
    -0.06
    .transition
    -0.06
    lant
    -0.06
    POSITIVE LOGITS
     durable
    0.07
    ).^
    0.07
    "]').
    0.06
    innerText
    0.06
    证
    0.05
    ',(
    0.05
    toFixed
    0.05
    ],[-
    0.05
     благ
    0.05
    母
    0.05
    Act Density 0.005%

    No Known Activations