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

    Neuronpedia

    INDEX
    Explanations

    social media and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overfitting
    0.50
     averse
    0.49
     indexing
    0.48
     jitter
    0.48
     reduct
    0.47
     uptick
    0.47
     aversion
    0.45
     presum
    0.45
     paltry
    0.44
     seeding
    0.44
    POSITIVE LOGITS
    omain
    0.53
    وسف
    0.52
    وبي
    0.49
     Fonds
    0.49
     Restaurant
    0.48
    充满
    0.48
    ojo
    0.47
     Multicultural
    0.47
     Hammers
    0.46
    usa
    0.46
    Act Density 0.000%

    No Known Activations