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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xen
    -0.06
     disputed
    -0.06
    straint
    -0.06
    füh
    -0.06
     Sitting
    -0.06
    aille
    -0.06
     outer
    -0.06
    .best
    -0.06
     один
    -0.06
    ait
    -0.06
    POSITIVE LOGITS
    ражд
    0.07
    .handleError
    0.07
    vro
    0.07
    _txt
    0.07
     kidding
    0.07
     handleError
    0.07
            
↵
↵
    0.06
    .TRAN
    0.06
     clarify
    0.06
                ↵            ↵
    0.06
    Act Density 0.010%

    No Known Activations