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

    Neuronpedia

    INDEX
    Explanations

    key concepts and mechanisms in discussions about systems or solutions

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

    main core essence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.50
     InputDecoration
    -0.49
     Tonic
    -0.48
    enderror
    -0.48
     createSlice
    -0.44
     kasarigan
    -0.43
     tonic
    -0.42
     Tumble
    -0.42
     FEES
    -0.42
     nationality
    -0.41
    POSITIVE LOGITS
    OGND
    0.49
     Administrativna
    0.39
     motivadoras
    0.39
     podjela
    0.38
     dasselbe
    0.37
     ujednoznacz
    0.36
    Ultimo
    0.36
    Tembelea
    0.36
     esencia
    0.36
    Principal
    0.36
    Act Density 0.055%

    No Known Activations