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

    Neuronpedia

    INDEX
    Explanations

    providing information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lilly
    -0.07
     Loving
    -0.06
    GLOBAL
    -0.06
     Minimal
    -0.06
     wiring
    -0.06
    .initialize
    -0.06
     　 　 　 　 　
    -0.06
     Oral
    -0.06
     EZ
    -0.06
    	Result
    -0.06
    POSITIVE LOGITS
     выяв
    0.07
     victim
    0.06
    groupBox
    0.06
     zby
    0.06
    .Color
    0.06
    ofday
    0.06
     contention
    0.06
     ว
    0.06
    ุปกรณ
    0.06
     sucker
    0.06
    Act Density 0.040%

    No Known Activations