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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks used in code or markup languages

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

    code snippets and string formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     olsa
    -0.39
     garrafa
    -0.38
     gydy
    -0.36
     escova
    -0.35
     citoy
    -0.35
     télécharger
    -0.35
     bañera
    -0.35
     caneta
    -0.34
     kılı
    -0.34
     kvinder
    -0.33
    POSITIVE LOGITS
     <>",
    1.06
     <=",
    0.87
     >=",
    0.82
    Personendaten
    0.71
     <",
    0.71
    WriteTagHelper
    0.69
    ."],
    0.61
    viewDidLoad
    0.60
     ?";
    0.60
    ?";
    0.60
    Act Density 0.277%

    No Known Activations