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

    Neuronpedia

    INDEX
    Explanations

    Therefore

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oningen
    -0.07
    ichten
    -0.07
     حاج
    -0.07
    isson
    -0.07
    تجار
    -0.07
     |-
    -0.07
     competition
    -0.06
    ⨭
    -0.06
     gorge
    -0.06
    ᶢ
    -0.06
    POSITIVE LOGITS
    	w
    0.07
    ве
    0.07
    捕鱼
    0.07
    Concern
    0.07
    inem
    0.07
     alertController
    0.07
     scape
    0.07
    -party
    0.07
     vaccinated
    0.06
    matic
    0.06
    Act Density 0.090%

    No Known Activations