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

    Neuronpedia

    INDEX
    Explanations

    file paths in a specific format

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

    relative paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rine
    -0.35
    \
    -0.35
    "]);
    -0.35
     requ
    -0.35
    اً
    -0.35
    ]);
    -0.35
    ு
    -0.34
    Font
    -0.34
    țion
    -0.33
    er
    -0.33
    POSITIVE LOGITS
    ('../
    2.45
    ('../../
    1.76
    ('../../../
    1.65
    ("../
    1.52
    ('./
    1.12
    ("../../
    1.00
    ("./
    0.94
    ="../
    0.85
    ("~/
    0.83
     ['./
    0.72
    Act Density 0.000%

    No Known Activations