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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to message passing and field definitions in a data structure

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

    repeated fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.54
     Schwert
    -0.41
    restaurants
    -0.41
     maisha
    -0.40
     <<<<<<<<<<<<<<
    -0.40
    WEBPACK
    -0.40
    kreuz
    -0.40
    endphp
    -0.39
    ionage
    -0.39
     angin
    -0.39
    POSITIVE LOGITS
     repeat
    1.37
     repetition
    1.23
     repeating
    1.22
     repeats
    1.20
    Repeat
    1.20
     repetir
    1.19
     Repeat
    1.18
     repeated
    1.18
    repeat
    1.17
     repeti
    1.13
    Act Density 0.096%

    No Known Activations