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

    Neuronpedia

    INDEX
    Explanations

    occurrences of programming-related annotations or metadata

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IContainer
    -0.47
    IVEREF
    -0.46
     salido
    -0.42
     &___
    -0.39
    ญิง
    -0.39
     caído
    -0.38
    inWeight
    -0.37
     protección
    -0.37
     ayudado
    -0.36
    BeforeMethod
    -0.36
    POSITIVE LOGITS
    src
    0.65
    ("~/
    0.56
    LEncoder
    0.52
     src
    0.50
    AnimationsModule
    0.49
     firmament
    0.49
     ***!
    0.49
     TextAlign
    0.48
    CrossOrigin
    0.47
     defaultstate
    0.47
    Act Density 0.000%

    No Known Activations