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

    Neuronpedia

    INDEX
    Explanations

    book database entries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Released
    -0.07
    	best
    -0.06
     yaw
    -0.06
     व
    -0.06
     перес
    -0.06
    Better
    -0.06
     needless
    -0.06
     pře
    -0.06
     푸
    -0.06
     भ
    -0.06
    POSITIVE LOGITS
    chematic
    0.06
    leshooting
    0.06
    erece
    0.06
    。',↵
    0.06
    sitemap
    0.06
     گیاه
    0.06
     GETGLOBAL
    0.06
     UIScreen
    0.06
    …”↵↵
    0.06
    =localhost
    0.05
    Act Density 0.321%

    No Known Activations