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

    Neuronpedia

    INDEX
    Explanations

    user directory names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informativo
    0.40
     психологи
    0.37
    共
    0.37
    ითხ
    0.35
    azole
    0.34
     psychological
    0.34
    iska
    0.34
    isez
    0.34
    eted
    0.33
    lok
    0.33
    POSITIVE LOGITS
    Desktop
    1.02
     Desktop
    0.94
    Downloads
    0.89
    Documents
    0.86
     desktop
    0.82
     Documents
    0.81
    桌面
    0.76
     Downloads
    0.73
     desktops
    0.71
    Pictures
    0.69
    Act Density 0.007%

    No Known Activations