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

    Neuronpedia

    INDEX
    Explanations

    Go

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pflicht
    -0.08
    絶
    -0.08
    isticas
    -0.08
    יצה
    -0.08
     tsch
    -0.08
     sicr
    -0.08
     absolute
    -0.07
     beep
    -0.07
     বাৰ
    -0.07
     duties
    -0.07
    POSITIVE LOGITS
     journalists
    0.08
     associate
    0.08
    vig
    0.07
    .Head
    0.07
     fundamentally
    0.07
     associates
    0.07
     transverse
    0.07
     scraped
    0.07
     semantics
    0.07
     modalités
    0.07
    Act Density 0.001%

    No Known Activations