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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    造
    -0.07
    วงศ
    -0.07
     Haven
    -0.07
    <r
    -0.07
    /how
    -0.07
    オリ
    -0.06
    _SOC
    -0.06
    :red
    -0.06
    격
    -0.06
    _tC
    -0.06
    POSITIVE LOGITS
    uvian
    0.07
     Exam
    0.06
     subscribed
    0.06
     PRODUCT
    0.06
     strained
    0.06
     mins
    0.06
    ONUS
    0.06
    cased
    0.05
    �
    0.05
    σπ
    0.05
    Act Density 0.001%

    No Known Activations