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

    Neuronpedia

    INDEX
    Explanations

    Arch Linux package installation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     robust
    0.76
     lâm
    0.74
     Schein
    0.73
     Captain
    0.68
     Kosten
    0.68
     Vend
    0.67
     frontline
    0.67
     Watershed
    0.66
    я
    0.66
     rightful
    0.64
    POSITIVE LOGITS
    GraphQL
    0.91
    toluene
    0.85
     agradable
    0.83
    NING
    0.80
    Includes
    0.80
    Imports
    0.79
    satz
    0.79
    sala
    0.78
     derivada
    0.77
     invertebr
    0.77
    Act Density 0.007%

    No Known Activations