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

    Neuronpedia

    INDEX
    Explanations

    Mountains

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hinge
    -0.07
     наз
    -0.06
     sharp
    -0.06
    ircles
    -0.06
    gems
    -0.06
    为什么
    -0.06
     Companion
    -0.06
     حک
    -0.06
     bene
    -0.06
     Books
    -0.06
    POSITIVE LOGITS
    asyon
    0.07
    ayla
    0.06
    221
    0.06
     endeavor
    0.06
    上海
    0.06
    Emma
    0.06
    18
    0.06
    esehen
    0.06
    활동
    0.06
     grayscale
    0.06
    Act Density 0.000%

    No Known Activations