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

    Neuronpedia

    INDEX
    Explanations

    potentially intimidating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     child
    0.42
     once
    0.41
     pie
    0.39
     pier
    0.39
    ports
    0.38
     cast
    0.38
    bag
    0.38
    perms
    0.38
    <start_of_image>
    0.38
    ri
    0.37
    POSITIVE LOGITS
    ເຄ
    0.47
    城乡
    0.43
    轂
    0.41
     Resistant
    0.41
     வட்ட
    0.41
    是由
    0.41
     हौ
    0.41
     Habana
    0.40
    ләре
    0.40
     મારી
    0.39
    Act Density 0.001%

    No Known Activations