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

    Neuronpedia

    INDEX
    Explanations

    the word "the" in various contexts and combinations

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

    identifying roles or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    벌
    -0.46
    razos
    -0.45
     strikes
    -0.44
    atience
    -0.42
     schloss
    -0.41
     offsets
    -0.41
    цездатний
    -0.41
     strike
    -0.40
    albeit
    -0.40
     challenges
    -0.40
    POSITIVE LOGITS
     AssemblyCompany
    0.88
    transQ
    0.59
     Houſe
    0.52
     Chriftian
    0.52
     perſon
    0.52
     himſelf
    0.52
    ſelf
    0.51
     Majefty
    0.49
     myſelf
    0.49
     Jefus
    0.48
    Act Density 0.031%

    No Known Activations