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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    question marks and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AntiForgeryToken
    -0.55
    -0.53
    Ārējās
    -0.49
     Biôgrafia
    -0.46
    WriteTagHelper
    -0.46
    WebElementEntity
    -0.44
    -0.44
     snippetHide
    -0.44
     Italijanski
    -0.43
     Infórmanos
    -0.43
    POSITIVE LOGITS
    ?)
    1.36
    ?).
    1.05
    ?):
    0.98
    ?),
    0.92
    ?]
    0.91
    ?")
    0.84
     ?)
    0.82
    ?”
    0.81
    ?}
    0.80
    ?')
    0.80
    Act Density 0.001%

    No Known Activations