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

    Neuronpedia

    INDEX
    Explanations

    client interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mortara
    1.03
     GERM
    0.93
    窨
    0.90
    anthemum
    0.87
     Darrell
    0.87
     vegetales
    0.86
    EMPT
    0.84
    alloween
    0.84
     extremism
    0.83
     turnips
    0.83
    POSITIVE LOGITS
     client
    2.89
     Client
    2.78
    client
    2.75
    Client
    2.75
     clients
    2.63
     Clients
    2.53
     CLIENT
    2.45
    clients
    2.35
    Clients
    2.35
    CLIENT
    2.30
    Act Density 0.856%

    No Known Activations