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

    Neuronpedia

    INDEX
    Explanations

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     th
    0.75
     UX
    0.71
     lemon
    0.71
    е
    0.70
     elegant
    0.69
     UI
    0.68
     sesame
    0.68
     tap
    0.68
     е
    0.67
    ният
    0.66
    POSITIVE LOGITS
    IL
    1.21
    AC
    1.18
    IMA
    1.14
    AN
    1.11
    ITest
    1.03
    ICA
    1.03
    IS
    1.02
    ARA
    1.01
    CO
    1.01
    AD
    1.00
    Act Density 0.354%

    No Known Activations