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

    Neuronpedia

    INDEX
    Explanations

    reach out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kommer
    0.75
     Away
    0.70
    carbons
    0.68
     malloc
    0.68
     continuum
    0.67
     background
    0.67
     Mientras
    0.66
     Jira
    0.65
    ocat
    0.65
     mocks
    0.65
    POSITIVE LOGITS
     vecchia
    0.77
     vieille
    0.70
    ফর্ম
    0.70
    льно
    0.70
    ழை
    0.69
     λοι
    0.69
    লাকে
    0.68
     раздел
    0.68
     velha
    0.68
     দ্বার
    0.66
    Act Density 0.119%

    No Known Activations