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

    Neuronpedia

    INDEX
    Explanations

    programming concepts and terminology related to coding languages

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

    reserved keyword

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.71
    LLocation
    -0.71
    MLLoader
    -0.71
    <end_of_turn>
    -0.70
    <unused71>
    -0.70
    ArgsConstructor
    -0.70
    <unused57>
    -0.69
    <unused31>
    -0.69
    <unused15>
    -0.69
    <unused45>
    -0.69
    POSITIVE LOGITS
     cam
    0.35
     touch
    0.28
     camp
    0.27
     verb
    0.27
     such
    0.27
    Technik
    0.27
     Cam
    0.26
    ,
    0.25
     or
    0.25
     These
    0.23
    Act Density 0.003%

    No Known Activations