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

    Neuronpedia

    INDEX
    Explanations

    .table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phelps
    -0.07
    6
    -0.06
    allenge
    -0.06
    Listeners
    -0.06
    ces
    -0.06
    orrent
    -0.06
     NV
    -0.06
     вода
    -0.06
     тепло
    -0.06
     κά
    -0.06
    POSITIVE LOGITS
    Maint
    0.06
     kdy
    0.06
     leds
    0.06
    avatars
    0.06
     hung
    0.06
    	token
    0.06
     bran
    0.06
     oversee
    0.06
     embar
    0.06
     Avatar
    0.06
    Act Density 0.001%

    No Known Activations