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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     @{↵
    -0.07
     وجود
    -0.06
     Как
    -0.06
     zwar
    -0.06
    附
    -0.06
    だ
    -0.06
     Uma
    -0.06
    uraa
    -0.06
    _correct
    -0.06
    尾
    -0.06
    POSITIVE LOGITS
     Vector
    0.07
    histor
    0.07
    /helper
    0.07
    Illustr
    0.07
    .Fragment
    0.06
     strands
    0.06
    _flux
    0.06
    .tagName
    0.06
    (Exception
    0.06
    .Many
    0.06
    Act Density 0.021%

    No Known Activations