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

    Neuronpedia

    INDEX
    Explanations

    Earth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     activities
    -0.08
    avan
    -0.07
     queens
    -0.07
     Chron
    -0.07
     routine
    -0.07
    prox
    -0.06
    anuts
    -0.06
     clique
    -0.06
     Activities
    -0.06
     vacations
    -0.06
    POSITIVE LOGITS
    ﻴ
    0.07
    onestly
    0.06
    -warning
    0.06
     anyway
    0.06
    —if
    0.06
    >'+↵
    0.06
     destek
    0.06
     údaj
    0.06
    >"+↵
    0.06
     رسم
    0.06
    Act Density 0.005%

    No Known Activations