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

    Neuronpedia

    INDEX
    Explanations

    initialisms and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WebSocket
    0.50
     Neutron
    0.46
     Udemy
    0.46
     didactic
    0.46
     nood
    0.45
     zealous
    0.45
    вую
    0.45
     webhook
    0.45
     Dramatic
    0.45
     baju
    0.45
    POSITIVE LOGITS
    MA
    0.94
    AP
    0.91
    PI
    0.90
    AS
    0.89
    AC
    0.89
    DA
    0.88
    DS
    0.86
    IS
    0.85
    FI
    0.84
    PA
    0.82
    Act Density 0.316%

    No Known Activations