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

    Neuronpedia

    INDEX
    Explanations

    Mixed data types and formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Дев
    -0.09
    _AUTHOR
    -0.09
    .Excel
    -0.08
    _PENDING
    -0.08
    ้อย
    -0.08
    embers
    -0.08
    ossiers
    -0.08
     vorgestellt
    -0.07
     vermittelt
    -0.07
    ത്തില
    -0.07
    POSITIVE LOGITS
     citas
    0.08
     cors
    0.08
     caminar
    0.08
     preacher
    0.07
    	ctx
    0.07
     tamaño
    0.07
     reproduced
    0.07
     temo
    0.07
    paste
    0.07
     styr
    0.07
    Act Density 0.001%

    No Known Activations