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

    Neuronpedia

    INDEX
    Explanations

    perfect tenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     evolves
    0.29
     snippets
    0.29
    evolving
    0.27
     recursive
    0.27
     accusation
    0.27
     annotation
    0.27
     refinements
    0.27
     validation
    0.27
     evolving
    0.26
     codewords
    0.26
    POSITIVE LOGITS
     endeavoured
    0.23
     Been
    0.22
     hurriedly
    0.22
     ティ
    0.22
     tirelessly
    0.22
    हेही
    0.22
     нередко
    0.22
    actionBarTab
    0.21
     ])
    0.21
     been
    0.21
    Act Density 0.010%

    No Known Activations