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

    Neuronpedia

    INDEX
    Explanations

    unified

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sim
    -0.07
    	vo
    -0.07
    simulation
    -0.06
    蒱
    -0.06
    ⎓
    -0.06
     winter
    -0.06
    网店
    -0.06
     dense
    -0.06
     Peer
    -0.06
    ספטמבר
    -0.06
    POSITIVE LOGITS
     UserManager
    0.07
    HR
    0.07
    	LP
    0.07
     headache
    0.06
    为何
    0.06
    疗法
    0.06
    햇
    0.06
    原来是
    0.06
     mediator
    0.06
     solução
    0.06
    Act Density 0.002%

    No Known Activations