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

    Neuronpedia

    INDEX
    Explanations

    time units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.75
    ScopeManager
    -0.75
     ]);
    -0.73
     enfans
    -0.72
    saraba
    -0.72
    "];
    -0.67
    GEBURTSDATUM
    -0.66
    '],
    -0.63
    "]);
    -0.63
     autorytatywna
    -0.63
    POSITIVE LOGITS
    '
    0.59
     Cracks
    0.51
     duration
    0.49
     dispense
    0.46
     visibility
    0.46
     silent
    0.46
     quantization
    0.46
     gloves
    0.45
     latency
    0.45
     ingest
    0.45
    Act Density 0.026%

    No Known Activations