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

    Neuronpedia

    INDEX
    Explanations

    causes and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     positioned
    0.48
     oaks
    0.46
     oak
    0.45
     ventured
    0.45
     perfused
    0.45
     pads
    0.45
     nyug
    0.44
     stream
    0.43
     wonders
    0.43
     situated
    0.42
    POSITIVE LOGITS
     કારણે
    0.51
    讫
    0.46
    導致
    0.46
     akibat
    0.44
    ally
    0.44
    :
    0.44
    的反
    0.43
     reveló
    0.43
     оказался
    0.42
    导致
    0.42
    Act Density 0.004%

    No Known Activations