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

    Neuronpedia

    INDEX
    Explanations

    regarding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dığ
    -0.08
    蒄
    -0.08
     confuse
    -0.07
     ssize
    -0.07
    .assertEqual
    -0.07
    .YELLOW
    -0.06
    (StringUtils
    -0.06
    わからない
    -0.06
    engeance
    -0.06
    RootElement
    -0.06
    POSITIVE LOGITS
     insulin
    0.07
    EDA
    0.07
     suggested
    0.07
     đồ
    0.07
     cứu
    0.07
    舟山
    0.06
    看好
    0.06
     Reno
    0.06
    ansa
    0.06
     unmanned
    0.06
    Act Density 0.001%

    No Known Activations