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

    Neuronpedia

    INDEX
    Explanations

    patterns of repeated dashes or underscores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code syntax and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.49
     ujednoznacz
    -0.44
    Xna
    -0.42
     ainfi
    -0.41
    ArrowToggle
    -0.41
    tolua
    -0.40
    istoitu
    -0.40
     camiset
    -0.40
     mauva
    -0.40
     rhestr
    -0.40
    POSITIVE LOGITS
    nasse
    0.50
    AxisAlignment
    0.50
     ());
    0.49
     )
    0.49
     }));
    0.48
     );
    0.48
     )}
    0.47
     }}\
    0.47
     }}}
    0.47
     <<<<<<<<<<<<<<
    0.47
    Act Density 0.049%

    No Known Activations