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

    Neuronpedia

    INDEX
    Explanations

    heterogeneous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    straints
    -0.06
     кто
    -0.06
     квітня
    -0.06
    .assertIs
    -0.06
     ami
    -0.06
    .PL
    -0.06
    (sql
    -0.06
    Li
    -0.06
     ReadOnly
    -0.06
    าบาล
    -0.06
    POSITIVE LOGITS
     heterogeneous
    0.10
    난
    0.07
     Giang
    0.07
     고
    0.07
     homogeneous
    0.07
     het
    0.07
    HG
    0.07
    '])){↵
    0.07
     Tanz
    0.07
     Ikea
    0.07
    Act Density 0.004%

    No Known Activations