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

    Neuronpedia

    INDEX
    Explanations

    ideologies and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ших
    0.45
     здійс
    0.44
     skorzyst
    0.42
     শরণার্থীরা
    0.41
    立つ
    0.41
     सम्मिलित
    0.41
    яс
    0.40
    ában
    0.40
    럇
    0.40
     Española
    0.40
    POSITIVE LOGITS
     ந
    0.53
    國內
    0.50
    Profile
    0.46
     Bar
    0.46
    Bar
    0.46
    crime
    0.45
     조
    0.44
     Chloe
    0.44
    Rol
    0.44
     किं
    0.43
    Act Density 0.005%

    No Known Activations