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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find the JavaScript snippet checking for the “is-external=true” substring in a URL.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     handmade
    -0.06
     Haziran
    -0.06
     Monad
    -0.06
    .fromJson
    -0.06
    voucher
    -0.06
     Besides
    -0.06
     strap
    -0.06
    .goto
    -0.06
     defe
    -0.06
    iena
    -0.06
    POSITIVE LOGITS
    awesome
    0.07
    FACT
    0.07
    dbg
    0.07
    İY
    0.07
    .Java
    0.07
    collapse
    0.07
     ESPN
    0.06
    BACKGROUND
    0.06
     freaking
    0.06
    _UNDER
    0.06
    Act Density 0.000%

    No Known Activations