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

    Neuronpedia

    INDEX
    Explanations

    absence or negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aff
    -0.07
    BL
    -0.07
     Đông
    -0.07
     cycl
    -0.06
    Certificate
    -0.06
     duty
    -0.06
    �
    -0.06
     alta
    -0.06
     zaměstnan
    -0.06
     pup
    -0.06
    POSITIVE LOGITS
    ******
↵
    0.06
    ώς
    0.06
    ！」↵↵
    0.06
    \":{\"
    0.06
    handle
    0.06
    ]
↵
    0.06
     поє
    0.06
    。如果
    0.06
    }%
    0.06
    redients
    0.06
    Act Density 0.145%

    No Known Activations