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

    Neuronpedia

    INDEX
    Explanations

    Gil names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Demo
    0.71
     теку
    0.69
    加入
    0.69
     Hälfte
    0.69
     Tü
    0.69
     risques
    0.68
    മായും
    0.68
    خوا
    0.68
    调
    0.67
    管
    0.67
    POSITIVE LOGITS
    berto
    1.07
    crist
    1.04
    iam
    1.01
    games
    1.00
    iland
    0.95
    ool
    0.89
    christ
    0.89
    cre
    0.88
    ardino
    0.86
    ermo
    0.85
    Act Density 0.006%

    No Known Activations