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

    Neuronpedia

    INDEX
    Explanations

    buy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Safety
    -0.06
    版本
    -0.06
     цен
    -0.06
    yeah
    -0.06
    Customers
    -0.06
    -bre
    -0.06
    		 ↵
    -0.06
    -report
    -0.06
     Pixels
    -0.06
    Bullet
    -0.05
    POSITIVE LOGITS
    UF
    0.07
    riel
    0.07
    iona
    0.07
    ismatch
    0.07
    ropa
    0.07
    Margins
    0.07
    _BC
    0.07
     dims
    0.07
    delimiter
    0.07
    prene
    0.06
    Act Density 0.022%

    No Known Activations