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

    Neuronpedia

    INDEX
    Explanations

    end of text or code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raquo
    0.38
    嘱
    0.38
    ;;
    0.37
     getType
    0.36
    潅
    0.36
    łów
    0.36
    Pues
    0.36
     большинство
    0.35
     keresztül
    0.35
     comparar
    0.35
    POSITIVE LOGITS
    /,
    0.57
    /)
    0.56
    /",
    0.52
    /}
    0.50
    /).
    0.48
    /}{
    0.47
    /</
    0.45
    /]
    0.44
    /");
    0.44
    /',
    0.44
    Act Density 0.003%

    No Known Activations