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

    Neuronpedia

    INDEX
    Explanations

    ool

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xmin
    -0.07
     Become
    -0.07
    +(
    -0.07
    xbe
    -0.06
    CanBeConverted
    -0.06
    }/${
    -0.06
     PCB
    -0.06
     ateş
    -0.06
    áh
    -0.06
    IGIN
    -0.06
    POSITIVE LOGITS
     wool
    0.18
     Wool
    0.17
    ool
    0.09
     Dra
    0.07
     blankets
    0.07
     quotas
    0.07
    질
    0.06
    rol
    0.06
    皮
    0.06
     rady
    0.06
    Act Density 0.002%

    No Known Activations