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

    Neuronpedia

    INDEX
    Explanations

    Side one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쿵
    -0.07
    盎
    -0.07
     AIM
    -0.07
    .ms
    -0.07
    baar
    -0.07
    🎯
    -0.07
    越
    -0.06
    Rails
    -0.06
    HOW
    -0.06
    برا
    -0.06
    POSITIVE LOGITS
    EI
    0.08
     يقدم
    0.07
    	L
    0.07
     lodash
    0.07
    ieves
    0.07
     LDL
    0.07
     absorption
    0.07
     overwrite
    0.07
     ε
    0.07
    psilon
    0.06
    Act Density 0.008%

    No Known Activations