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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lands
    -0.07
     gan
    -0.07
     producing
    -0.06
    Lista
    -0.06
     ryb
    -0.06
     wallpapers
    -0.06
     下
    -0.06
     gg
    -0.06
    _highlight
    -0.06
     Merc
    -0.06
    POSITIVE LOGITS
    stdafx
    0.06
    _WITH
    0.06
    '',
    0.06
    еи
    0.06
     Farms
    0.06
    _Application
    0.06
     свет
    0.06
    ARM
    0.06
     chce
    0.05
     FIND
    0.05
    Act Density 0.194%

    No Known Activations