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

    Neuronpedia

    INDEX
    Explanations

    word constraints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Appendix
    0.40
    ില
    0.34
    घव
    0.33
    ըն
    0.33
    CPR
    0.32
     Appendix
    0.32
    жа
    0.30
     homoc
    0.30
    dateTime
    0.30
     verbunden
    0.30
    POSITIVE LOGITS
    lify
    0.33
     gesturing
    0.32
     Show
    0.31
    äft
    0.31
    强制
    0.31
     Seen
    0.30
     سریع
    0.30
     reputation
    0.30
     riddle
    0.30
     زیبا
    0.30
    Act Density 0.000%

    No Known Activations