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

    Neuronpedia

    INDEX
    Explanations

    references to technological advancements or capabilities

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

    Follows conjunctions, prepositions, or articles

    np_acts-logits-general · gemini-2.0-flash

    next level, special software, simple lampposts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -1.01
    
    -0.81
     ujednoznacz
    -0.74
    RetentionPolicy
    -0.72
    "?>
    -0.69
    DockStyle
    -0.66
     auffi
    -0.65
     kasarigan
    -0.64
     CreateTagHelper
    -0.63
    ionalmente
    -0.63
    POSITIVE LOGITS
    SequentialGroup
    0.53
     jut
    0.52
    MIDDLEWARE
    0.51
     computerized
    0.50
     géant
    0.50
     sleek
    0.49
    잘
    0.48
    ⅕
    0.48
     thingy
    0.47
     experto
    0.47
    Act Density 0.536%

    No Known Activations