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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash

    This neuron detects numeric version strings (e.g. the “x.y.z” version numbers) in changelog headings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    زيد
    -0.07
    _shipping
    -0.07
    Advertisement
    -0.06
    
↵

↵
    -0.06
     �
    -0.06
     photoshop
    -0.06
    lrt
    -0.06
     plaisir
    -0.06
    .getId
    -0.06
    )])↵↵
    -0.06
    POSITIVE LOGITS
     //(
    0.07
     secretion
    0.07
     بالا
    0.07
     methyl
    0.06
     els
    0.06
     illuminate
    0.06
     vend
    0.06
     onBind
    0.06
     ศ
    0.06
     cavalry
    0.06
    Act Density 0.002%

    No Known Activations