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

    Neuronpedia

    INDEX
    Explanations

    programming commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shipments
    -0.08
     rush
    -0.08
    ポイント
    -0.08
     trú
    -0.08
     shy
    -0.08
    .mo
    -0.08
     hens
    -0.07
     râ
    -0.07
     mach
    -0.07
     Rush
    -0.07
    POSITIVE LOGITS
    Overwrite
    0.08
     ಹೊಸ
    0.08
    replacement
    0.08
    Brick
    0.08
     Нов
    0.08
    Replacing
    0.08
    overwrite
    0.08
    Tape
    0.08
    Replacement
    0.08
     العصر
    0.08
    Act Density 0.000%

    No Known Activations