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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron detects code assignments to email header properties (e.g. setting the From or To fields in a mail‐sending API).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Loader
    -0.06
    opian
    -0.06
    stoff
    -0.06
     ferry
    -0.06
    áticas
    -0.06
    Viewport
    -0.06
    bsites
    -0.06
    puter
    -0.06
     Falk
    -0.06
     университ
    -0.06
    POSITIVE LOGITS
    _completion
    0.07
    532
    0.06
     марш
    0.06
    .
    0.06
     éc
    0.06
     가장
    0.06
    -position
    0.06
     him
    0.06
    irc
    0.06
     khoảng
    0.06
    Act Density 0.005%

    No Known Activations