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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thank
    -0.08
    (org
    -0.07
    }]
    -0.07
     changes
    -0.07
     lead
    -0.07
     ::=
    -0.07
     GDPR
    -0.07
     πραγμα
    -0.07
     Rifle
    -0.07
     Essentially
    -0.06
    POSITIVE LOGITS
    TREE
    0.07
     Default
    0.06
     рес
    0.06
     Midlands
    0.06
    iVar
    0.06
    бот
    0.05
     ایشان
    0.05
     кер
    0.05
    Š
    0.05
    	client
    0.05
    Act Density 0.037%

    No Known Activations