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

    Neuronpedia

    INDEX
    Explanations

    creative works and literature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iq
    0.51
    wa
    0.50
    la
    0.50
    co
    0.49
    po
    0.49
    o
    0.48
    g
    0.48
    oo
    0.47
    RI
    0.47
     working
    0.46
    POSITIVE LOGITS
     작품
    0.60
     œuvres
    0.59
    作品
    0.54
     произведение
    0.53
     obras
    0.52
     œuvre
    0.52
     произведения
    0.50
     作品
    0.49
     masterpieces
    0.49
     karya
    0.47
    Act Density 0.003%

    No Known Activations