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

    Neuronpedia

    INDEX
    Explanations

    @Table, Table

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    早早
    -0.08
    收拾
    -0.07
     SD
    -0.07
    颛
    -0.07
    TreeWidgetItem
    -0.07
     Sega
    -0.07
    迪士
    -0.07
    appropriate
    -0.07
    谟
    -0.07
    خذ
    -0.07
    POSITIVE LOGITS
     tokenizer
    0.07
     pollut
    0.07
    Word
    0.06
     )"
    0.06
     '?
    0.06
     truncated
    0.06
    -dominated
    0.06
    /antlr
    0.06
    的主题
    0.06
     Exec
    0.06
    Act Density 0.001%

    No Known Activations