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

    Neuronpedia

    INDEX
    Explanations

    say "Road" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Digital
    -0.06
    енными
    -0.06
     Shib
    -0.06
    Wide
    -0.06
     McN
    -0.06
     Khan
    -0.06
     Heavy
    -0.06
     –
    -0.06
     Guantanamo
    -0.06
    abstract
    -0.06
    POSITIVE LOGITS
    。不
    0.07
     camouflage
    0.07
    이지
    0.07
     iOS
    0.06
    (choice
    0.06
     <!
    0.06
     HttpResponseMessage
    0.06
    找
    0.06
    ош
    0.06
     ничего
    0.06
    Act Density 0.000%

    No Known Activations