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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires whenever it sees a “this.” instance‐member access (especially private fields prefixed with an underscore).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .LEADING
    -0.07
     film
    -0.06
     threads
    -0.06
     attic
    -0.06
    aged
    -0.06
     stall
    -0.06
    .Footer
    -0.06
    _linear
    -0.06
    mine
    -0.06
    alled
    -0.06
    POSITIVE LOGITS
     znovu
    0.07
     hodnoty
    0.06
    변
    0.06
    wik
    0.06
    _fmt
    0.06
     hitting
    0.06
    린
    0.06
    siz
    0.06
    .stat
    0.06
     argv
    0.06
    Act Density 0.015%

    No Known Activations