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

    Neuronpedia

    INDEX
    Explanations

    org

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     europe
    -0.08
     �
    -0.06
     SMP
    -0.06
     출장
    -0.06
     McB
    -0.06
     alleging
    -0.06
    Maintenance
    -0.06
     Hydraulic
    -0.06
    Probe
    -0.06
     verbess
    -0.06
    POSITIVE LOGITS
     ],↵
    0.07
     oath
    0.07
    _GRANTED
    0.07
    ?")↵
    0.06
     wg
    0.06
    	find
    0.06
    Inspect
    0.06
    UILayout
    0.06
    	load
    0.06
     ner
    0.06
    Act Density 0.001%

    No Known Activations