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

    Neuronpedia

    INDEX
    Explanations

    instances of brackets and dollar signs, indicating mathematical notation or expressions

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

    code syntax with symbols and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    qtype
    -0.60
     ujednoznacz
    -0.59
     vectoriales
    -0.57
    quelize
    -0.53
    ChildScrollView
    -0.50
    ViewFeatures
    -0.49
     ModelRenderer
    -0.49
     mówią
    -0.48
     wijze
    -0.48
     canina
    -0.47
    POSITIVE LOGITS
    {$
    1.34
     {$
    0.96
    }{$
    0.72
     ($
    0.70
    ($
    0.70
     $
    0.67
    /$
    0.66
    |}{$
    0.66
     "$
    0.66
    :$
    0.65
    Act Density 0.080%

    No Known Activations