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

    Neuronpedia

    INDEX
    Explanations

    VHS tapes and emails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     einz
    0.80
     حالا
    0.71
     jonka
    0.70
     Acá
    0.70
     ночью
    0.68
     பெண்ண
    0.68
    निश्ड
    0.68
     metabolism
    0.67
     ตอน
    0.67
     consumir
    0.66
    POSITIVE LOGITS
    链
    0.83
     chain
    0.74
    ließ
    0.74
     fevere
    0.72
    =(
    0.69
     preval
    0.69
     heartfelt
    0.69
    ходит
    0.69
     maintenance
    0.69
     booth
    0.69
    Act Density 0.000%

    No Known Activations