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

    Neuronpedia

    INDEX
    Explanations

    respectivement, respectively, respectively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -,
    0.43
     And
    0.41
    ,
    0.39
    %,
    0.34
    +,
    0.34
    !,
    0.33
     Sorry
    0.32
    性和
    0.32
     Everything
    0.32
    ですし
    0.32
    POSITIVE LOGITS
     ஆகியோர்
    0.49
     각각
    0.47
    それぞれ
    0.46
    respectively
    0.43
     are
    0.42
     quienes
    0.42
     respectivement
    0.42
    それぞれの
    0.41
     respectivamente
    0.41
     jeweils
    0.40
    Act Density 0.150%

    No Known Activations