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

    Neuronpedia

    INDEX
    Explanations

    lists with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -,
    0.43
     ойношот
    0.41
    いたり
    0.40
     predicates
    0.40
     لار
    0.40
     मरी
    0.40
    等的
    0.40
    鰓
    0.39
     masts
    0.39
     faucets
    0.39
    POSITIVE LOGITS
     lastly
    0.51
     Lastly
    0.44
     infine
    0.40
     Trou
    0.39
    StudioProjects
    0.37
     Face
    0.36
    Lastly
    0.36
    毕竟
    0.35
     Trouble
    0.35
    还有一个
    0.35
    Act Density 0.166%

    No Known Activations