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

    Neuronpedia

    INDEX
    Explanations

    Bee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vlastně
    -0.08
     Ful
    -0.07
     всього
    -0.07
     logical
    -0.07
    Interest
    -0.07
     blacklist
    -0.07
    敷
    -0.06
     remote
    -0.06
    无
    -0.06
     republice
    -0.06
    POSITIVE LOGITS
     destin
    0.06
    ...)↵
    0.06
     Portug
    0.06
     amatør
    0.06
    VISIBLE
    0.06
    ويك
    0.06
    &M
    0.06
    BW
    0.05
     віт
    0.05
     andra
    0.05
    Act Density 0.000%

    No Known Activations