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

    Neuronpedia

    INDEX
    Explanations

    Pres

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Server
    0.67
     Servers
    0.66
     servers
    0.66
    servers
    0.64
    server
    0.61
     server
    0.59
     SERVER
    0.55
     сервер
    0.55
    Server
    0.54
    SERVER
    0.50
    POSITIVE LOGITS
     preserving
    1.17
     conserving
    1.16
     conserv
    1.12
     conservation
    1.12
     сохра
    1.12
     preservation
    1.11
    Conservation
    1.11
     حفظ
    1.10
     conservar
    1.10
    保
    1.09
    Act Density 0.001%

    No Known Activations