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

    Neuronpedia

    INDEX
    Explanations

    code, functions, and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ）・
    0.57
    」「
    0.47
    ですし
    0.44
    !),
    0.42
    했고
    0.42
    »),
    0.42
    었고
    0.42
     있으며
    0.42
    ))&&(
    0.39
    ）、
    0.37
    POSITIVE LOGITS
    ↵↵↵↵
    0.86
    ↵↵↵↵↵
    0.82
    ↵↵↵
    0.81
    ↵↵↵↵↵↵↵
    0.73
    ↵↵↵↵↵↵↵↵
    0.73
    ↵↵↵↵↵↵
    0.72
    ↵↵↵↵↵↵↵↵↵
    0.66
    ↵↵↵↵↵↵↵↵↵↵
    0.65
    ↵↵↵↵↵↵↵↵↵↵↵
    0.61
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.59
    Act Density 0.403%

    No Known Activations