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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     прекрас
    -0.08
    ruptcy
    -0.07
     Le
    -0.07
     همسر
    -0.07
     nhuận
    -0.07
    ---
    -0.07
    ########################
    -0.07
     (!
    -0.07
     Conference
    -0.07
    .Le
    -0.07
    POSITIVE LOGITS
    yc
    0.06
     mashed
    0.06
     FFT
    0.06
    ductor
    0.06
    อนไลน
    0.06
    .reduce
    0.05
     systemctl
    0.05
    итися
    0.05
    �
    0.05
    айт
    0.05
    Act Density 0.008%

    No Known Activations