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

    Neuronpedia

    INDEX
    Explanations

    understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tank
    -0.07
     venez
    -0.07
    .find
    -0.07
    顯
    -0.06
    829
    -0.06
    .ToolStripButton
    -0.06
     Tables
    -0.06
    显
    -0.06
    john
    -0.06
    _IRQHandler
    -0.06
    POSITIVE LOGITS
    ठन
    0.07
    .tp
    0.07
     lays
    0.06
    ))*
    0.06
     phenomenon
    0.06
     fury
    0.06
    }*
    0.06
    .MiddleRight
    0.06
    ypo
    0.06
    bounds
    0.06
    Act Density 0.079%

    No Known Activations