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

    Neuronpedia

    INDEX
    Explanations

    conditional logic

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens used in step‐by‐step instructions or procedural guides (imperative steps in tutorials).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     excursion
    -0.07
    Reuters
    -0.07
     UNIVERSITY
    -0.06
     flourish
    -0.06
     Üniversitesi
    -0.06
    pc
    -0.06
    blend
    -0.06
    _bed
    -0.06
    _De
    -0.06
    sudo
    -0.06
    POSITIVE LOGITS
     desperation
    0.07
    .NewReader
    0.06
    ique
    0.06
     *)__
    0.06
    =Y
    0.06
    chi
    0.06
    phrase
    0.06
     rewritten
    0.06
     şek
    0.06
    ointment
    0.06
    Act Density 0.054%

    No Known Activations