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

    Neuronpedia

    INDEX
    Explanations

    stars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     legalization
    -0.10
     hinein
    -0.08
    內容
    -0.08
     thematic
    -0.08
     dictated
    -0.08
     textos
    -0.08
     tape
    -0.08
     legalized
    -0.08
     costume
    -0.08
     texts
    -0.08
    POSITIVE LOGITS
    附近
    0.12
    Nearby
    0.10
     அருக
    0.10
     Nearby
    0.09
     located
    0.09
     nearby
    0.09
     Azul
    0.09
     주변
    0.09
    _neighbors
    0.08
     Francisco
    0.08
    Act Density 0.015%

    No Known Activations