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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter "l" in various positions

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

    installation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wikipagina
    -0.50
     spørgsmål
    -0.50
    ódnica
    -0.47
     Wikiseite
    -0.47
    Tembelea
    -0.46
     Ooster
    -0.46
     Insel
    -0.45
    fromnode
    -0.45
    Tikang
    -0.45
    Хьажоргаш
    -0.45
    POSITIVE LOGITS
    The
    0.50
    isn
    0.44
     })
    0.44
    Ằ
    0.43
    ).)
    0.42
     The
    0.42
     SSM
    0.42
    ()))
    0.42
    ')))
    0.42
    SSM
    0.42
    Act Density 0.006%

    No Known Activations