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

    Neuronpedia

    INDEX
    Explanations

    erts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    那么
    -0.07
    lite
    -0.06
    隆
    -0.06
     indiscrim
    -0.06
     Illuminate
    -0.06
     business
    -0.06
    الث
    -0.06
     fug
    -0.06
     century
    -0.05
    -feature
    -0.05
    POSITIVE LOGITS
    -task
    0.07
     地
    0.07
    :↵
    0.07
    ají
    0.06
    lé
    0.06
    ！↵
    0.06
    schema
    0.06
    ardi
    0.06
    ८
    0.06
    ่น
    0.06
    Act Density 0.000%

    No Known Activations