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

    Neuronpedia

    INDEX
    Explanations

    computer code and encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pretend
    -0.07
     जरूर
    -0.07
     pessoais
    -0.07
    拿
    -0.07
    (priority
    -0.07
     priorities
    -0.07
     व्यक्ति
    -0.07
     perplex
    -0.07
     philosopher
    -0.07
    所得
    -0.07
    POSITIVE LOGITS
     notation
    0.12
     shorthand
    0.12
     abstra
    0.11
     succinct
    0.11
    notation
    0.11
    Notation
    0.11
    compact
    0.10
     summarize
    0.10
     компакт
    0.10
    まとめ
    0.10
    Act Density 0.017%

    No Known Activations