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

    Neuronpedia

    INDEX
    Explanations

    domain grant reduces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    period
    0.39
    translateX
    0.38
    EEC
    0.37
    ထိ
    0.36
    winter
    0.36
    printing
    0.36
    ឱ
    0.36
     GL
    0.35
    Repeat
    0.35
    ジェ
    0.35
    POSITIVE LOGITS
    izzeria
    0.43
     vestiges
    0.42
    悚
    0.42
     siamo
    0.42
    rances
    0.42
     rhymes
    0.40
     stigmat
    0.39
     비밀
    0.39
    érie
    0.39
    alanya
    0.39
    Act Density 0.000%

    No Known Activations