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

    Neuronpedia

    INDEX
    Explanations

    Assembly and Reflection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     l
    0.71
    ib
    0.65
    >
    0.61
    ah
    0.59
    ek
    0.58
     lifeline
    0.58
     market
    0.57
    нын
    0.57
    atani
    0.57
    it
    0.55
    POSITIVE LOGITS
     ancienne
    0.68
     encontraron
    0.61
    ב
    0.60
    ટ
    0.59
     éclair
    0.59
     extraño
    0.58
    Up
    0.57
     способности
    0.57
     encont
    0.57
    ριο
    0.56
    Act Density 0.001%

    No Known Activations