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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    the neuron activates on numeric literals (especially floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     framing
    -0.06
     Vale
    -0.06
    रत
    -0.06
    enheim
    -0.06
    ivial
    -0.06
     Les
    -0.06
    ammers
    -0.06
     Surprise
    -0.06
     ligne
    -0.06
    .layers
    -0.06
    POSITIVE LOGITS
    },"
    0.07
    ้ม
    0.06
    @endsection
    0.06
     />';↵
    0.06
    _al
    0.06
     dealing
    0.06
    .hasClass
    0.06
     shl
    0.06
    .virtual
    0.06
    ?";↵
    0.06
    Act Density 0.001%

    No Known Activations