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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    นาด
    -0.06
    arto
    -0.06
    광역시
    -0.06
    train
    -0.06
    kg
    -0.06
    uckland
    -0.06
    аются
    -0.06
    éra
    -0.06
    Depart
    -0.06
    enta
    -0.06
    POSITIVE LOGITS
     Animal
    0.07
     }]);↵
    0.07
     animal
    0.07
     perfil
    0.07
     catal
    0.07
     Tes
    0.06
     amplify
    0.06
     mixed
    0.06
     fam
    0.06
     climate
    0.06
    Act Density 0.012%

    No Known Activations