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

    Neuronpedia

    INDEX
    Explanations

    end of time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    [
    -1.76
    ３
    -1.59
    .
    -1.55
     人
    -1.55
    Ｄ
    -1.54
     registró
    -1.51
    왑
    -1.48
    UCION
    -1.47
    Didn
    -1.45
    Doing
    -1.42
    POSITIVE LOGITS
     the
    1.82
    簠
    1.66
     freaking
    1.48
    袿
    1.45
     their
    1.43
     見える
    1.41
     this
    1.39
    şiv
    1.38
     大きい
    1.38
    FOREWORD
    1.32
    Act Density 0.011%

    No Known Activations