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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations related to calculus, particularly derivatives and simplifications

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

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     voces
    -0.32
     sandalias
    -0.30
     Quels
    -0.29
     wielding
    -0.29
    itzender
    -0.29
     místa
    -0.28
     takže
    -0.28
    ۜ
    -0.28
     cejas
    -0.28
     alors
    -0.27
    POSITIVE LOGITS
    expandindo
    0.70
     noDo
    0.69
    ⎦
    0.65
     ExecuteAsync
    0.63
     تضيفلها
    0.62
     MainAxisSize
    0.61
    oneofs
    0.59
     ModelExpression
    0.59
     snippetHide
    0.57
    Tikang
    0.56
    Act Density 0.022%

    No Known Activations