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

    Neuronpedia

    INDEX
    Explanations

    Towers, bell towers, architecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     идет
    -0.09
    -0.09
     preconce
    -0.09
     ਰਹ
    -0.08
    �
    -0.08
     consommation
    -0.08
     Receita
    -0.07
    ivaa
    -0.07
     Ion
    -0.07
     revisar
    -0.07
    POSITIVE LOGITS
     clocks
    0.10
     tower
    0.09
     reloj
    0.09
     dome
    0.09
     towers
    0.09
     relóg
    0.09
     ringing
    0.09
     skyscr
    0.09
     roofs
    0.08
     drums
    0.08
    Act Density 0.015%
    No Known Activations