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

    Neuronpedia

    INDEX
    Explanations

    programming types and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    టమి
    0.48
    angers
    0.47
     سپاه
    0.45
    resher
    0.45
    isphere
    0.45
    kult
    0.44
    лове
    0.44
    郘
    0.44
    系的
    0.43
    ण्ड
    0.43
    POSITIVE LOGITS
     e
    0.41
     that
    0.41
     vimos
    0.40
    ת
    0.38
     έν
    0.38
     voyez
    0.38
     enjo
    0.37
    Spotify
    0.37
     Ainda
    0.36
    ମ
    0.36
    Act Density 0.001%

    No Known Activations