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

    Neuronpedia

    INDEX
    Explanations

    Philosophy and Science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hate
    -0.08
    hog
    -0.07
     proje
    -0.07
     cama
    -0.07
     dav
    -0.07
     enrolling
    -0.07
    入住
    -0.07
     channels
    -0.07
     offset
    -0.07
     donors
    -0.07
    POSITIVE LOGITS
     astronom
    0.11
     astronomy
    0.10
     UFO
    0.09
     বিজ্ঞান
    0.09
     विज्ञान
    0.09
     Astronomy
    0.09
     الرياض
    0.09
     scientist
    0.09
    NASA
    0.08
     Monsanto
    0.08
    Act Density 0.036%

    No Known Activations