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

    Neuronpedia

    INDEX
    Explanations

    elle

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dialogue
    -0.07
    Serialize
    -0.07
    operators
    -0.06
    472
    -0.06
     cooler
    -0.06
    รายงาน
    -0.06
     projecting
    -0.06
     Vog
    -0.06
     solitude
    -0.06
    	current
    -0.06
    POSITIVE LOGITS
    namespace
    0.06
    nell
    0.06
     mute
    0.06
     Müz
    0.06
    /met
    0.06
     крас
    0.06
    	namespace
    0.05
     Dee
    0.05
    ',{'
    0.05
    uš
    0.05
    Act Density 0.004%

    No Known Activations