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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" in various contexts

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

    on followed by location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ParallelGroup
    -0.42
    In
    -0.39
     In
    -0.38
     sobretudo
    -0.38
    เย็น
    -0.37
     gì
    -0.36
     certeza
    -0.36
     tangki
    -0.35
     apapun
    -0.35
    jenigen
    -0.35
    POSITIVE LOGITS
     الحره
    0.75
    TypedDataSet
    0.68
     дописавши
    0.66
     Administrativna
    0.65
     ivelany
    0.65
    Tembelea
    0.65
    ſelves
    0.58
     odkazy
    0.57
    falfa
    0.54
    getBoard
    0.54
    Act Density 0.041%

    No Known Activations