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

    Neuronpedia

    INDEX
    Explanations

    Internal Company Systems

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on software or information-system names and other multi-letter uppercase acronyms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     услов
    -0.07
     staged
    -0.06
    strength
    -0.06
    ارف
    -0.06
    ้ำหน
    -0.06
     стрем
    -0.06
    _fps
    -0.06
    ذ
    -0.06
    .Highlight
    -0.06
     усл
    -0.06
    POSITIVE LOGITS
    .setAuto
    0.07
    .handleChange
    0.06
     Faith
    0.06
     Flickr
    0.06
    sun
    0.06
    ournals
    0.06
    Leave
    0.06
    WARN
    0.06
     удив
    0.06
    사람
    0.06
    Act Density 0.031%

    No Known Activations