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

    Neuronpedia

    INDEX
    Explanations

    environment variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nummer
    -0.09
    -0.07
    ;
↵
↵/
    -0.07
     selectors
    -0.07
     subdiv
    -0.07
     hil
    -0.07
     Warren
    -0.07
    编号
    -0.07
     accented
    -0.07
    .prop
    -0.07
    POSITIVE LOGITS
    ściej
    0.09
    roga
    0.08
     ọna
    0.08
    -être
    0.08
    emon
    0.08
    ån
    0.08
    {}{
    0.08
    Nie
    0.08
    óviles
    0.08
     ""}↵
    0.08
    Act Density 0.074%
    No Known Activations