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

    Neuronpedia

    INDEX
    Explanations

    legal proceedings and judicial decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.78
    ंधन
    0.75
    ੋ
    0.74
    imeters
    0.73
    거운
    0.71
     pursuits
    0.70
     topology
    0.70
    ]";
    0.69
    kt
    0.69
    al
    0.68
    POSITIVE LOGITS
    द
    0.81
    trom
    0.77
     gavel
    0.75
    t
    0.74
     fain
    0.73
    0.72
     feas
    0.71
    سر
    0.71
    ্ণ
    0.71
     заработной
    0.69
    Act Density 0.033%

    No Known Activations