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

    Neuronpedia

    INDEX
    Explanations

    includes protecting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Möglichkeit
    1.23
     unpublished
    1.15
     cortisol
    1.14
     tapered
    1.12
     TLS
    1.12
     compl
    1.12
     flares
    1.08
    ]).
    1.07
     specified
    1.07
     vignette
    1.07
    POSITIVE LOGITS
    ilidad
    1.24
    в
    1.17
    ouring
    1.15
    𝑜
    1.11
    𝑒
    1.09
    tego
    1.08
    te
    1.04
    Bharat
    1.04
    ità
    1.03
     лица
    1.03
    Act Density 0.022%

    No Known Activations