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

    Neuronpedia

    INDEX
    Explanations

    gr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     muze
    -0.08
     corp
    -0.08
     migraines
    -0.07
     orgas
    -0.07
     Deloitte
    -0.07
     chamb
    -0.07
    .modal
    -0.07
    拳
    -0.07
    (Audio
    -0.07
    ోల
    -0.07
    POSITIVE LOGITS
     settlers
    0.15
     immigrants
    0.10
     newcomers
    0.10
     прибы
    0.10
     missionaries
    0.09
     founders
    0.09
     kolon
    0.09
     founding
    0.09
     pioneers
    0.09
     komm
    0.09
    Act Density 0.020%

    No Known Activations