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

    Neuronpedia

    INDEX
    Explanations

    anticoagulation treatment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emerg
    -0.07
    edith
    -0.06
    鸡
    -0.06
     backpage
    -0.06
    NonNull
    -0.06
     facing
    -0.06
     arrog
    -0.06
     변경
    -0.06
    _activation
    -0.06
     Monitoring
    -0.06
    POSITIVE LOGITS
    …………
    0.06
    coal
    0.06
    ']="
    0.06
    臺灣
    0.05
    	first
    0.05
    εδ
    0.05
    0.05
    /a
    0.05
     globe
    0.05
     firstName
    0.05
    Act Density 0.020%

    No Known Activations