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

    Neuronpedia

    INDEX
    Explanations

    greeting "hello"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    speople
    0.73
    א
    0.73
    )",
    0.70
    ง่าย
    0.67
    ק
    0.65
    ים
    0.64
     Wenn
    0.63
     kendine
    0.63
    ።
    0.61
     মো
    0.58
    POSITIVE LOGITS
    il
    0.71
    cribed
    0.70
    D
    0.69
     a
    0.68
    ли
    0.66
    amate
    0.66
    thought
    0.65
    pura
    0.65
     reorganized
    0.65
    creas
    0.64
    Act Density 0.001%

    No Known Activations