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

    Neuronpedia

    INDEX
    Explanations

    references to recent activity or history of watched content

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

    history and last actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.56
    AndroidJUnit
    -0.53
     كومونز
    -0.52
    EndInit
    -0.50
    äude
    -0.48
     يتيمه
    -0.48
    Tikang
    -0.48
     Wiktionnaire
    -0.47
     NSCoder
    -0.46
    ➌
    -0.45
    POSITIVE LOGITS
     memory
    0.45
     Memory
    0.43
     history
    0.40
     histories
    0.40
     Hist
    0.39
     History
    0.39
    SequentialGroup
    0.37
    retten
    0.37
     histor
    0.36
     errors
    0.36
    Act Density 0.186%

    No Known Activations