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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lavish
    -0.07
    fout
    -0.07
    Macro
    -0.07
    ièrement
    -0.07
    criptors
    -0.07
    佛
    -0.06
    /ne
    -0.06
    -Free
    -0.06
     Automated
    -0.06
     epith
    -0.06
    POSITIVE LOGITS
    /'↵↵
    0.07
     stratej
    0.07
     χρησιμοποι
    0.06
     ειδ
    0.06
     Authenticate
    0.06
     영향
    0.06
    .orm
    0.06
    	async
    0.06
    	describe
    0.06
     Düş
    0.06
    Act Density 0.046%

    No Known Activations