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

    Neuronpedia

    INDEX
    Explanations

    title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deemed
    -0.06
    커스
    -0.06
    rtle
    -0.06
     uży
    -0.06
     Forever
    -0.06
    /new
    -0.06
    taxonomy
    -0.06
     chví
    -0.06
     Metodo
    -0.06
     далі
    -0.06
    POSITIVE LOGITS
    具体
    0.07
    min
    0.07
    _'+
    0.06
    елеф
    0.06
    )$
    0.06
     tissues
    0.06
    ould
    0.06
    \">
    0.06
    -med
    0.06
     applicant
    0.06
    Act Density 0.004%

    No Known Activations