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

    Neuronpedia

    INDEX
    Explanations

    and or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consultants
    -0.07
     blasting
    -0.06
     день
    -0.06
    帕
    -0.06
    ющими
    -0.06
     Exhaust
    -0.06
     Procedure
    -0.06
     Through
    -0.06
     moms
    -0.05
    	dt
    -0.05
    POSITIVE LOGITS
     siti
    0.07
     firearms
    0.07
    ो
    0.07
     telecommunications
    0.07
    есп
    0.07
    anch
    0.06
    ,
↵
    0.06
     advancements
    0.06
    hind
    0.06
    _CAMERA
    0.06
    Act Density 0.044%

    No Known Activations