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

    Neuronpedia

    INDEX
    Explanations

    Job postings

    np_max-act · gemini-2.0-flash

    The neuron activates on phrasing that spells out applicant requirements or qualifications (e.g. “must,” “be,” “able,” “you,” “require”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .za
    -0.07
    Element
    -0.07
    .Remote
    -0.06
    ường
    -0.06
     Dict
    -0.06
     amid
    -0.06
    еров
    -0.06
    .Assembly
    -0.06
     reloading
    -0.06
    Ya
    -0.06
    POSITIVE LOGITS
     захворювання
    0.07
     робити
    0.07
     warto
    0.06
     recep
    0.06
    anuts
    0.06
     разви
    0.06
     metod
    0.06
     disruptive
    0.06
     ajust
    0.06
    sında
    0.06
    Act Density 0.032%

    No Known Activations