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

    Neuronpedia

    INDEX
    Explanations

    steering wheel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ант
    0.84
     ਨਹੀਂ
    0.70
     neće
    0.69
    Den
    0.68
    Rac
    0.68
    Rit
    0.68
    -
    0.67
    Eth
    0.67
    Bad
    0.66
     superconductors
    0.66
    POSITIVE LOGITS
     revista
    0.87
    ómago
    0.86
    o
    0.81
     revistas
    0.80
    herjee
    0.80
    েন্টে
    0.78
    楽し
    0.78
    isomer
    0.77
    gramModel
    0.76
    mbito
    0.76
    Act Density 0.002%

    No Known Activations