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

    Neuronpedia

    INDEX
    Explanations

    coding loops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Driver
    -0.06
     boots
    -0.06
    막
    -0.06
     AH
    -0.06
    aders
    -0.06
    Clark
    -0.06
    "Yeah
    -0.06
    	arg
    -0.06
     Dent
    -0.06
    像
    -0.06
    POSITIVE LOGITS
    려고
    0.06
     پوش
    0.06
    setColor
    0.06
     HEL
    0.06
     gebru
    0.06
    icits
    0.06
     Ariel
    0.06
     трет
    0.06
     quota
    0.06
    .credentials
    0.06
    Act Density 0.022%

    No Known Activations