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

    Neuronpedia

    INDEX
    Explanations

    Tumor induction

    np_acts-logits-general · gemini-2.5-flash-lite

    legal and official document formatting, particularly court case headings and reference numbers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     court
    -1.01
     courts
    -1.01
     Courts
    -0.94
    courts
    -0.86
    court
    -0.82
    Court
    -0.79
     jury
    -0.79
     doughnut
    -0.78
     Court
    -0.78
     juries
    -0.77
    POSITIVE LOGITS
    cisive
    0.91
     ")[
    0.90
    filtr
    0.87
     Protestants
    0.86
    styled
    0.81
    intervento
    0.81
     intervención
    0.81
     intervention
    0.80
     agency
    0.80
     участи
    0.80
    Act Density 0.068%

    No Known Activations