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

    Neuronpedia

    INDEX
    Explanations

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tra
    -0.07
    grades
    -0.06
     glare
    -0.06
     };
↵
↵
    -0.06
    _word
    -0.06
    opening
    -0.06
     crops
    -0.06
    кар
    -0.06
     corn
    -0.06
     Feel
    -0.06
    POSITIVE LOGITS
    UNET
    0.08
     вним
    0.06
    .linkedin
    0.06
    YGON
    0.06
     ≤
    0.06
    .confirm
    0.06
    ummings
    0.06
    (lbl
    0.06
    .metadata
    0.06
    ），
    0.06
    Act Density 0.003%

    No Known Activations