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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elpers
    -0.07
    ровать
    -0.06
     Going
    -0.06
     Du
    -0.06
    alg
    -0.06
     installations
    -0.06
    -success
    -0.06
     prosperity
    -0.06
     tối
    -0.06
     Girls
    -0.06
    POSITIVE LOGITS
     volum
    0.08
    .So
    0.07
    .?
    0.07
    .invoke
    0.07
    вердж
    0.07
    ],'
    0.06
     شامل
    0.06
    ereo
    0.06
    鑑
    0.06
    ému
    0.06
    Act Density 0.082%

    No Known Activations