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

    Neuronpedia

    INDEX
    Explanations

    own death or absence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    विष्ट
    0.79
     lương
    0.71
     അള
    0.71
     പ്രവർത്തി
    0.70
     config
    0.68
     Ciencia
    0.66
    Coefficient
    0.66
     പ്രവര്‍ത്തി
    0.66
     Risk
    0.66
    ancias
    0.65
    POSITIVE LOGITS
     demise
    1.81
     downfall
    1.45
     death
    1.43
     eventual
    1.38
     disappearance
    1.32
    death
    1.23
     deaths
    1.18
     extinction
    1.16
     destruction
    1.16
     untimely
    1.09
    Act Density 0.061%

    No Known Activations