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

    Neuronpedia

    INDEX
    Explanations

    consistently ranks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     succession
    0.45
     designations
    0.45
     designation
    0.44
     ratings
    0.42
    衡量
    0.42
     likelihood
    0.42
    Ratings
    0.40
    เดินทาง
    0.40
     Ratings
    0.39
     disparity
    0.39
    POSITIVE LOGITS
     Placing
    0.96
     placing
    0.94
     placed
    0.91
     finished
    0.90
     finishing
    0.88
     finish
    0.86
     Finished
    0.84
     قرار
    0.81
     finishes
    0.80
    placed
    0.80
    Act Density 0.008%

    No Known Activations