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

    Neuronpedia

    INDEX
    Explanations

    instances of populations and their characteristics within a data context

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

    entities with describing words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.33
    Temp
    -0.29
     and
    -0.29
    :
    -0.27
    TypeError
    -0.27
    date
    -0.25
    ,
    -0.24
    again
    -0.24
    (++
    -0.24
     instead
    -0.23
    POSITIVE LOGITS
    AndEndTag
    0.75
    AddTagHelper
    0.75
     ModelExpression
    0.71
     InputDecoration
    0.69
    TestingModule
    0.69
    providedIn
    0.69
    RenderAtEndOf
    0.68
     transfieras
    0.68
     BoxDecoration
    0.68
    <pad>
    0.67
    Act Density 0.115%

    No Known Activations