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

    Neuronpedia

    INDEX
    Explanations

    advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tu
    -0.06
    แนว
    -0.06
    Fortunately
    -0.06
     programmes
    -0.06
    648
    -0.06
     veřej
    -0.06
    escort
    -0.06
     Courtesy
    -0.06
    ограм
    -0.06
     However
    -0.06
    POSITIVE LOGITS
    .property
    0.07
    тии
    0.07
     MIC
    0.07
     отли
    0.06
     Plays
    0.06
    _blank
    0.06
     //{
↵
    0.06
     цій
    0.06
     {{
    0.06
    .Ptr
    0.06
    Act Density 0.013%

    No Known Activations