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

    Neuronpedia

    INDEX
    Explanations

    learning python codecademy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ikken
    0.74
    石头
    0.74
     💕
    0.73
     °,
    0.73
     💞
    0.71
     superiority
    0.70
     Beta
    0.70
    <unused8>
    0.69
     অঞ্চল
    0.69
    😗
    0.69
    POSITIVE LOGITS
    parser
    0.71
    Mod
    0.67
    Sub
    0.67
    cod
    0.66
    Hunter
    0.66
    parse
    0.64
    mod
    0.64
    oxyd
    0.62
    parquet
    0.62
     Hunter
    0.61
    Act Density 0.021%

    No Known Activations