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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remot
    -0.07
     paramet
    -0.07
     mes
    -0.07
     logout
    -0.06
     rapport
    -0.06
     Lid
    -0.06
     TERMIN
    -0.06
     volunteered
    -0.06
    license
    -0.06
     Mandarin
    -0.06
    POSITIVE LOGITS
     �
    0.07
    одав
    0.06
    íše
    0.06
    _marshall
    0.06
     Hanson
    0.06
     Inspiration
    0.06
     leveraging
    0.06
     Siri
    0.06
     receptions
    0.06
    ीर
    0.06
    Act Density 0.546%

    No Known Activations