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
     UNIVERSITY
    -0.07
     Naming
    -0.06
    γμα
    -0.06
    -win
    -0.06
     cubes
    -0.06
    ipheral
    -0.06
    Ln
    -0.06
     nay
    -0.06
    729
    -0.06
     University
    -0.06
    POSITIVE LOGITS
     Доб
    0.06
    -door
    0.06
    .GO
    0.06
    flip
    0.06
    .hasMore
    0.06
     совсем
    0.06
    股东
    0.06
     investig
    0.06
     EDM
    0.06
    .fin
    0.06
    Act Density 0.026%

    No Known Activations