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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    希望大家
    -0.07
    朴素
    -0.07
    _logo
    -0.07
    眾
    -0.07
    平凡
    -0.07
    .Library
    -0.07
    硔
    -0.07
    倏
    -0.06
     Shared
    -0.06
    ':['
    -0.06
    POSITIVE LOGITS
    昃
    0.07
     retention
    0.07
    ensa
    0.07
    �
    0.07
     therap
    0.06
     thaw
    0.06
    \"",↵
    0.06
    _reaction
    0.06
     :";↵
    0.06
     '%$
    0.06
    Act Density 0.100%

    No Known Activations