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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Modules
    -0.08
    012
    -0.07
    152
    -0.07
    .Initialize
    -0.07
     kc
    -0.07
    Injector
    -0.07
    .Stream
    -0.07
    andise
    -0.07
     вне
    -0.07
     Governments
    -0.06
    POSITIVE LOGITS
     آثار
    0.07
    sock
    0.06
     шлях
    0.06
     iniciar
    0.06
     аж
    0.06
    OMPI
    0.06
    тесь
    0.06
     ขนาด
    0.06
     brav
    0.06
    xAF
    0.05
    Act Density 0.029%

    No Known Activations