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

    Neuronpedia

    INDEX
    Explanations

    timing and customization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sebuah
    0.77
    jav
    0.72
     étudiant
    0.70
     apparence
    0.69
    論文
    0.67
    memiş
    0.67
     प्रतिष्ठा
    0.66
     vizsgál
    0.66
     ఉన్న
    0.65
     egy
    0.65
    POSITIVE LOGITS
    Timing
    0.85
     timing
    0.81
     Timing
    0.80
     *=
    0.77
     timings
    0.76
    Customize
    0.75
     mileage
    0.75
     Pace
    0.75
     optional
    0.74
     velcro
    0.73
    Act Density 0.867%

    No Known Activations