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

    Neuronpedia

    INDEX
    Explanations

    knees bent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     internships
    0.80
     signings
    0.76
     compels
    0.75
     cellulosic
    0.75
     interesados
    0.74
     headwinds
    0.73
     stakeholders
    0.73
     synthes
    0.73
     championships
    0.73
     servings
    0.73
    POSITIVE LOGITS
    া
    0.90
    є
    0.89
    児童
    0.87
    eur
    0.81
     raccol
    0.81
    ш
    0.80
    лна
    0.80
    ρι
    0.79
    sap
    0.79
    uomo
    0.78
    Act Density 0.001%

    No Known Activations