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

    Neuronpedia

    INDEX
    Explanations

    JSON delimiters and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ”
    1.22
    ↵↵↵↵
    0.98
    ↵↵↵
    0.95
    」
    0.93
    ↵↵↵↵↵
    0.90
    ֽ
    0.87
    ׃
    0.84
     (-)
    0.84
    ”]
    0.84
    ]
    0.84
    POSITIVE LOGITS
    (),
    3.05
     "",
    2.99
     '',
    2.88
     [],
    2.80
     {},
    2.76
    !,
    2.74
    ₂,
    2.73
    [],
    2.70
    **,
    2.68
    '',
    2.66
    Act Density 0.588%

    No Known Activations