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

    Neuronpedia

    INDEX
    Explanations

    tr

    np_max-act · gemini-2.0-flash

    This neuron activates on HTML/XML markup tokens (e.g. tags like <table>, <tr>, <td>, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    itra
    -0.06
     Hava
    -0.06
     پخش
    -0.06
    	suite
    -0.06
    	Local
    -0.06
    .There
    -0.06
    finally
    -0.06
    .Sync
    -0.06
    isNew
    -0.06
    ---------------↵
    -0.06
    POSITIVE LOGITS
     electrónico
    0.06
     Problem
    0.06
    wizard
    0.06
     vague
    0.06
     cone
    0.06
     panor
    0.06
    naissance
    0.06
     Irish
    0.06
    �
    0.06
    _THAN
    0.06
    Act Density 0.005%

    No Known Activations