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

    Neuronpedia

    INDEX
    Explanations

    free will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     punctatis
    0.47
    াকার
    0.46
     бойынша
    0.40
    蕁
    0.38
    を務
    0.37
     سبسڈی
    0.37
    subfigure
    0.36
    癢
    0.36
    ഒ
    0.36
     తేదీ
    0.35
    POSITIVE LOGITS
    bies
    0.96
    zers
    0.82
    bie
    0.81
    🆓
    0.76
     lance
    0.72
    zing
    0.71
    form
    0.65
     roam
    0.63
     flowing
    0.62
    flowing
    0.61
    Act Density 0.040%

    No Known Activations