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

    Neuronpedia

    INDEX
    Explanations

    instances of ellipsis or incomplete thoughts in text

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

    directory paths and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     miniaturka
    -0.51
    erçe
    -0.51
     camiset
    -0.49
    PickerController
    -0.49
     Dansk
    -0.48
     kysy
    -0.48
    SEGUIR
    -0.48
    actéristi
    -0.46
     colectivo
    -0.46
     indígen
    -0.45
    POSITIVE LOGITS
    ..
    1.65
     '..
    1.62
     ..
    1.56
     "..
    1.47
    )..
    1.45
    '..
    1.38
    ..)
    1.29
    .."
    1.29
    "..
    1.27
    -..
    1.15
    Act Density 0.016%

    No Known Activations