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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Downtown
    -0.07
     πα
    -0.06
     svm
    -0.06
     scratches
    -0.06
    blr
    -0.06
    Diagnostic
    -0.06
    illion
    -0.06
    حي
    -0.06
     пал
    -0.06
    궁
    -0.06
    POSITIVE LOGITS
    -l
    0.07
    (metadata
    0.06
     scrim
    0.06
     expense
    0.06
     [["
    0.06
    .toJSON
    0.06
    <File
    0.06
     tether
    0.06
    .....
    0.06
     ['',
    0.06
    Act Density 0.003%

    No Known Activations