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

    Neuronpedia

    INDEX
    Explanations

    strat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distinguishing
    -0.08
     swell
    -0.07
     реб
    -0.07
    nard
    -0.07
    TEST
    -0.07
     Birch
    -0.07
    MESS
    -0.07
    ılıyor
    -0.07
    QUEST
    -0.07
    옳
    -0.07
    POSITIVE LOGITS
     fileType
    0.08
     Grupo
    0.07
    标准
    0.07
     Workshop
    0.07
    based
    0.07
     director
    0.07
    	project
    0.07
     strategy
    0.07
     dependent
    0.07
    _minute
    0.07
    Act Density 0.004%

    No Known Activations