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

    Neuronpedia

    INDEX
    Explanations

    first-person singular pronouns and associated references

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

    I thinking, I saying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.70
     NIS
    -0.51
    ly
    -0.50
    omore
    -0.49
    Carne
    -0.48
    hort
    -0.47
    The
    -0.47
    cess
    -0.47
    curity
    -0.46
    unya
    -0.46
    POSITIVE LOGITS
    colgante
    0.59
    farwyddwr
    0.54
    RefNanny
    0.48
    Спољашње
    0.46
    ślę
    0.45
    PositiveButton
    0.44
    Kanpo
    0.44
    richTextPanel
    0.43
    BagConstraints
    0.42
    цездатний
    0.42
    Act Density 0.166%

    No Known Activations