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

    Neuronpedia

    INDEX
    Explanations

    answering questions and explaining details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     updating
    0.65
     almost
    0.54
     current
    0.53
     identifying
    0.52
     working
    0.52
    ierende
    0.52
     unknown
    0.51
     cell
    0.51
     late
    0.51
     arguably
    0.51
    POSITIVE LOGITS
    <unused473>
    0.70
    établissement
    0.69
    quen
    0.68
    <unused276>
    0.68
    <unused941>
    0.68
     bhavati
    0.67
     trattamento
    0.67
    ሎጂ
    0.67
     tratamiento
    0.66
    𒌑
    0.66
    Act Density 0.256%

    No Known Activations