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

    Neuronpedia

    INDEX
    Explanations

    common prepositions and articles used in sentences

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

    days of the week

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     financières
    -0.43
     criatura
    -0.37
     profundamente
    -0.36
     borracha
    -0.36
     cueva
    -0.36
     térmico
    -0.36
     dessen
    -0.36
     raça
    -0.36
     deseja
    -0.35
     oculta
    -0.35
    POSITIVE LOGITS
     Monday
    1.20
     Wednesday
    1.19
    Monday
    1.16
    Wednesday
    1.16
     monday
    1.15
     Friday
    1.14
     wednesday
    1.13
     Tuesday
    1.13
     Thursday
    1.13
    Friday
    1.12
    Act Density 0.026%

    No Known Activations