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

    Neuronpedia

    INDEX
    Explanations

    most common, fundamental, primary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.58
     that
    0.41
     항상
    0.40
     음악
    0.39
    อย่าง
    0.39
    اي
    0.38
    를
    0.37
     다
    0.37
    가
    0.37
     이상의
    0.36
    POSITIVE LOGITS
     custo
    0.50
     tota
    0.50
     бути
    0.50
     respon
    0.47
     suport
    0.47
     actief
    0.46
     corpo
    0.46
    ++){
    0.46
     Munic
    0.45
    ंप
    0.44
    Act Density 0.074%

    No Known Activations