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

    Neuronpedia

    INDEX
    Explanations

    unmodified human, extended health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     donned
    0.47
     debes
    0.46
     compromised
    0.46
     Clip
    0.46
     loaded
    0.44
     CLI
    0.43
     *
    0.43
     money
    0.43
     CLL
    0.41
     Lucas
    0.41
    POSITIVE LOGITS
     három
    0.53
    serviceTime
    0.49
     첨
    0.49
     स्थ
    0.47
     മുഴുവ
    0.47
     spacetime
    0.46
     刺繍
    0.46
     tři
    0.46
     парамет
    0.45
     كث
    0.45
    Act Density 0.006%

    No Known Activations