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

    Neuronpedia

    INDEX
    Explanations

    file paths or references to local files in a coding context

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

    `.` or relative paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſtre
    -0.49
     solicitudes
    -0.45
     pouvoit
    -0.45
    StateList
    -0.44
     légal
    -0.44
    "]))
    -0.44
     incendie
    -0.43
     auroit
    -0.43
     feroit
    -0.42
    ']))
    -0.42
    POSITIVE LOGITS
    ('./
    2.27
    ("./
    1.21
     ['./
    1.20
    ('../
    1.16
    ('../../
    0.95
    ('../../../
    0.90
    './
    0.88
    ="./
    0.79
    ("../../
    0.79
     ./
    0.74
    Act Density 0.001%

    No Known Activations