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

    Neuronpedia

    INDEX
    Explanations

    numbers and estimates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.76
     -
    0.69
     (
    0.67
      
    0.65
     за
    0.63
    is
    0.62
     *
    0.60
    ↵
    0.58
     vs
    0.57
     be
    0.55
    POSITIVE LOGITS
     congressional
    1.00
     securities
    0.90
     trillion
    0.89
    hattis
    0.88
    jobSize
    0.87
    INSTDIR
    0.86
     numerose
    0.85
     nCmd
    0.85
     numerosi
    0.85
     दर्जन
    0.85
    Act Density 0.000%

    No Known Activations