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

    Neuronpedia

    INDEX
    Explanations

    controller

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zusammensch
    -0.09
     orta
    -0.08
     zusammeng
    -0.08
     crescente
    -0.08
     colle
    -0.08
     torno
    -0.08
     Alibaba
    -0.08
     tengah
    -0.08
    umpulan
    -0.07
     panjang
    -0.07
    POSITIVE LOGITS
     multifunction
    0.09
     antigen
    0.09
     landmarks
    0.08
     designation
    0.08
    (animation
    0.08
     competente
    0.08
     élu
    0.08
    _skin
    0.08
     spécialis
    0.08
     DESIGN
    0.07
    Act Density 0.002%

    No Known Activations