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

    Neuronpedia

    INDEX
    Explanations

    prior to action or specification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ignore
    0.82
    occur
    0.80
    an
    0.79
    Loc
    0.79
    assembling
    0.79
    allow
    0.76
    INS
    0.75
    occurring
    0.74
    to
    0.73
    does
    0.71
    POSITIVE LOGITS
     FirebaseAuth
    0.89
     Kafka
    0.83
     limitations
    0.82
     stel
    0.82
     于
    0.80
     KFC
    0.80
    讲述
    0.79
    兵
    0.79
     QoS
    0.79
     llamado
    0.78
    Act Density 0.001%

    No Known Activations