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

    Neuronpedia

    INDEX
    Explanations

    software tools and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FAILURE
    0.55
    Ошибка
    0.52
     personenbez
    0.51
    computers
    0.50
     recounts
    0.50
    aranth
    0.49
     computadora
    0.48
    ussy
    0.48
     determinante
    0.48
     unchanging
    0.48
    POSITIVE LOGITS
     tools
    1.13
     powerful
    1.02
     toolkit
    0.97
     integrations
    0.97
     features
    0.97
     tool
    0.96
     tooling
    0.95
     Tools
    0.95
     capabilities
    0.95
     ecosystem
    0.95
    Act Density 3.430%

    No Known Activations