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

    Neuronpedia

    INDEX
    Explanations

    rows and columns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gummies
    -0.08
    符
    -0.08
     recompensa
    -0.08
    ಿಐ
    -0.08
    ころ
    -0.07
     gummies
    -0.07
     despl
    -0.07
     МВД
    -0.07
     ranc
    -0.07
    Endian
    -0.07
    POSITIVE LOGITS
    (latitude
    0.09
    sharing
    0.09
     shared
    0.09
    shared
    0.09
    Sharing
    0.09
    Shared
    0.09
     neighboring
    0.08
     horizontal
    0.08
    latitude
    0.08
     compartilhar
    0.08
    Act Density 0.011%

    No Known Activations