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

    Neuronpedia

    INDEX
    Explanations

    remaining in place

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ®
    -0.07
     Implementation
    -0.07
     Governments
    -0.07
    .NO
    -0.07
    Government
    -0.07
    .Uri
    -0.07
     McKenzie
    -0.06
    .sheet
    -0.06
    Members
    -0.06
    Services
    -0.06
    POSITIVE LOGITS
    υμ
    0.08
     vou
    0.07
     intending
    0.06
     spaces
    0.06
    deen
    0.06
    AREA
    0.06
     امید
    0.06
     sens
    0.06
    spotify
    0.06
     spacing
    0.06
    Act Density 0.018%

    No Known Activations