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

    Neuronpedia

    INDEX
    Explanations

    Code/Data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confirmPassword
    -0.07
    couz
    -0.06
     xxxx
    -0.06
    стю
    -0.06
    배송
    -0.06
    地址
    -0.06
    욱
    -0.06
     strtoupper
    -0.06
    496
    -0.06
    агато
    -0.06
    POSITIVE LOGITS
     tres
    0.07
     lectures
    0.07
    collection
    0.07
     Comey
    0.06
     Representation
    0.06
     être
    0.06
     SM
    0.06
    	client
    0.06
    �
    0.06
     \""
    0.06
    Act Density 0.008%

    No Known Activations