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

    Neuronpedia

    INDEX
    Explanations

    crisis helplines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tobacco
    0.90
     terapé
    0.84
     medication
    0.83
    待遇
    0.80
     therapeutic
    0.80
     tuberculosis
    0.78
    ന്മ
    0.77
     addiction
    0.76
    藥
    0.76
     Tobin
    0.76
    POSITIVE LOGITS
     SpaceX
    0.60
     distance
    0.59
     UTC
    0.57
     Khanna
    0.57
     night
    0.56
    Distance
    0.56
     ফর্ম
    0.55
     کپ
    0.55
     cabling
    0.55
     Distance
    0.54
    Act Density 0.095%

    No Known Activations