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

    Neuronpedia

    INDEX
    Explanations

    praising you for exceptional performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adultery
    0.41
     hoping
    0.40
    udian
    0.39
     trying
    0.37
    耔
    0.37
    となります
    0.37
    儕
    0.37
    primarily
    0.36
     harap
    0.36
    carros
    0.36
    POSITIVE LOGITS
     skillfully
    0.81
     admirably
    0.78
     excellently
    0.76
     deserve
    0.75
     impressively
    0.71
     thoughtfully
    0.70
     successfully
    0.70
     beautifully
    0.70
     deserves
    0.69
    Successfully
    0.69
    Act Density 0.015%

    No Known Activations