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

    Neuronpedia

    INDEX
    Explanations

    to learn and use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Em
    0.78
    Priv
    0.74
    Be
    0.70
    Del
    0.69
    Ча
    0.69
    或其他
    0.69
    曾
    0.66
    Pert
    0.66
     తీవ్ర
    0.66
    Pre
    0.64
    POSITIVE LOGITS
     navigate
    1.18
     manage
    1.12
     setup
    1.06
     이해
    1.04
     deploy
    1.02
     구현
    1.01
     handling
    1.01
     Understand
    1.01
     التعامل
    1.00
     understand
    1.00
    Act Density 0.270%

    No Known Activations