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

    Neuronpedia

    INDEX
    Explanations

    server startup and management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     death
    0.43
     resp
    0.43
     PK
    0.42
     fury
    0.41
     frenzy
    0.41
    damageCount
    0.40
     मृत्यू
    0.40
     respiratoires
    0.39
     victim
    0.38
     Squid
    0.38
    POSITIVE LOGITS
    IVER
    0.45
    opener
    0.43
    Dedicated
    0.42
    JVM
    0.42
    OPS
    0.41
    Startup
    0.40
    iterrows
    0.40
    Sab
    0.40
    Shut
    0.40
    Terminal
    0.40
    Act Density 0.007%

    No Known Activations