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

    Neuronpedia

    INDEX
    Explanations

    after time-related events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     तब
    0.90
    avenir
    0.87
     pasir
    0.80
    ع
    0.79
    જર
    0.78
     கீழ்
    0.78
    ിലേക്ക്
    0.78
    номер
    0.77
    др
    0.77
    前
    0.76
    POSITIVE LOGITS
    noons
    1.14
    math
    1.06
    WARDS
    1.03
     shave
    1.02
    words
    1.02
     awhile
    0.98
    thoughts
    0.96
    ward
    0.96
    wards
    0.94
    effects
    0.91
    Act Density 0.081%

    No Known Activations