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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     correspondence
    -0.07
     supplemented
    -0.06
    cite
    -0.06
    міну
    -0.06
     appealing
    -0.06
     Ordered
    -0.06
    “To
    -0.06
    -0.06
     propose
    -0.06
    _MINUS
    -0.06
    POSITIVE LOGITS
    pwd
    0.07
     Plugin
    0.07
    워크
    0.07
    ещ
    0.07
     thúc
    0.07
    .");
↵
    0.06
    ...
↵
    0.06
     CIM
    0.06
    δρα
    0.06
     wag
    0.06
    Act Density 0.047%

    No Known Activations