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

    Neuronpedia

    INDEX
    Explanations

    about websites and books

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ращ
    -0.07
    .Wrap
    -0.07
    .trace
    -0.07
    /filter
    -0.06
    admin
    -0.06
    	admin
    -0.06
     threads
    -0.06
     Cand
    -0.06
     Uint
    -0.06
    /sample
    -0.06
    POSITIVE LOGITS
    ButtonType
    0.07
    ену
    0.07
    illard
    0.06
     bast
    0.06
    ██
    0.06
    ۲۷
    0.06
     estilo
    0.06
     ко
    0.06
    食
    0.06
     fon
    0.06
    Act Density 0.245%

    No Known Activations