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

    Neuronpedia

    INDEX
    Explanations

    corporate control and influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Arts
    0.53
    adon
    0.51
     FIC
    0.50
     School
    0.49
    अगर
    0.49
    ador
    0.49
    IT
    0.49
    ART
    0.49
    Museum
    0.48
    Arts
    0.48
    POSITIVE LOGITS
     are
    0.59
     suing
    0.52
     masks
    0.51
     attorneys
    0.51
     сум
    0.49
     blurry
    0.48
     حتى
    0.48
     tó
    0.48
     hikers
    0.47
     trucks
    0.47
    Act Density 0.030%

    No Known Activations