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

    Neuronpedia

    INDEX
    Explanations

    don't + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     instruction
    0.55
     instructions
    0.52
     restrictions
    0.51
    צי
    0.49
     commanding
    0.49
    在
    0.48
    ים
    0.48
     domination
    0.48
     in
    0.47
     duplication
    0.47
    POSITIVE LOGITS
     đừng
    0.64
     jangan
    0.63
    expect
    0.59
    ce
    0.58
    eské
    0.57
     underestimate
    0.57
    jangan
    0.57
    ėtų
    0.55
    長く
    0.54
     believe
    0.53
    Act Density 0.057%

    No Known Activations