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
    \\.
    -0.07
     Fan
    -0.06
    ець
    -0.06
     chtěl
    -0.06
    tat
    -0.06
    {}.
    -0.06
     Gh
    -0.05
     Message
    -0.05
     Trap
    -0.05
    	  ↵
    -0.05
    POSITIVE LOGITS
    .offsetHeight
    0.08
    VF
    0.07
    .ndim
    0.07
    /errors
    0.07
     FPGA
    0.07
    นาม
    0.07
    olis
    0.07
    _locator
    0.06
    Xã
    0.06
    quota
    0.06
    Act Density 0.002%

    No Known Activations